Dataset Viewer
Auto-converted to Parquet Duplicate
images
images listlengths
1
1
data_source
stringclasses
1 value
reward_model
dict
extra_info
dict
prompt
listlengths
2
2
ability
stringclasses
1 value
env_name
stringclasses
1 value
sealvqa_spatial
{ "ground_truth": "Yes, the hot dog is on the right side of the cup." }
{ "answer": "Yes, the hot dog is on the right side of the cup.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000558840.jpg", "index": "sealvqa_spatial_0", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the hot dog on the right side of the cup?" }, { "from": "gpt", "value": "Yes, the hot dog is on the right side of the cup." } ], "question": "Is the hot dog on the right side of the cup?", "question_id": "sealvqa_spatial_0", "search": 1, "target_instances": [ { "bbox": [ 199.84, 200.46, 77.71, 70.88 ], "instance_id": "", "name": "hot dog" }, { "bbox": [ 1.92, 87.91, 34.95, 175.35 ], "instance_id": "", "name": "cup" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the hot dog on the right side of the cup?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The handbag is to the left of the dog." }
{ "answer": "The handbag is to the left of the dog.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000116061.jpg", "index": "sealvqa_spatial_1", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the handbag to the left or right of the dog?" }, { "from": "gpt", "value": "The handbag is to the left of the dog." } ], "question": "Is the handbag to the left or right of the dog?", "question_id": "sealvqa_spatial_1", "search": 1, "target_instances": [ { "bbox": [ 213.81, 192.39, 53.94, 70.28 ], "instance_id": "", "name": "dog" }, { "bbox": [ 34.31, 135.73, 39.98, 75.62 ], "instance_id": "", "name": "handbag" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the handbag to the left or right of the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the handbag is on the left side of the bottle." }
{ "answer": "Yes, the handbag is on the left side of the bottle.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000116061.jpg", "index": "sealvqa_spatial_2", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the handbag on the left side of the bottle?" }, { "from": "gpt", "value": "Yes, the handbag is on the left side of the bottle." } ], "question": "Is the handbag on the left side of the bottle?", "question_id": "sealvqa_spatial_2", "search": 1, "target_instances": [ { "bbox": [ 34.31, 135.73, 39.98, 75.62 ], "instance_id": "", "name": "handbag" }, { "bbox": [ 240.52, 182.44, 11.23, 30.92 ], "instance_id": "", "name": "bottle" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the handbag on the left side of the bottle?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the dog is not above the motorcycle." }
{ "answer": "No, the dog is not above the motorcycle.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000400728.jpg", "index": "sealvqa_spatial_3", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the dog on the left side of the motorcycle?" }, { "from": "gpt", "value": "No, the dog is not on the left side of the motorcycle." }, { "from": "human", "value": "Is the dog above the motorcycle?" }, { "from": "gpt", "value": "No, the dog is not above the motorcycle." } ], "question": "Is the dog above the motorcycle?", "question_id": "sealvqa_spatial_3", "search": 1, "target_instances": [ { "bbox": [ 289.47, 214.76, 52.47, 72.72 ], "instance_id": "", "name": "dog" }, { "bbox": [ 146.02, 125.28, 79.47, 65.02 ], "instance_id": "", "name": "motorcycle" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the dog above the motorcycle?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the traffic light is above the person." }
{ "answer": "Yes, the traffic light is above the person.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000370210.jpg", "index": "sealvqa_spatial_4", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the traffic light on the left side of the person?" }, { "from": "gpt", "value": "No, the traffic light is not on the left side of the person." }, { "from": "human", "value": "Is the traffic light above the person?" }, { "from": "gpt", "value": "Yes, the traffic light is above the person." } ], "question": "Is the traffic light above the person?", "question_id": "sealvqa_spatial_4", "search": 1, "target_instances": [ { "bbox": [ 222.92, 143.43, 15.47, 39.41 ], "instance_id": "", "name": "person" }, { "bbox": [ 257.66, 80.96, 13.78, 22.04 ], "instance_id": "", "name": "traffic light" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the traffic light above the person?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the car is not on the left side of the person." }
{ "answer": "No, the car is not on the left side of the person.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000370210.jpg", "index": "sealvqa_spatial_5", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the car on the left side of the person?" }, { "from": "gpt", "value": "No, the car is not on the left side of the person." } ], "question": "Is the car on the left side of the person?", "question_id": "sealvqa_spatial_5", "search": 1, "target_instances": [ { "bbox": [ 222.92, 143.43, 15.47, 39.41 ], "instance_id": "", "name": "person" }, { "bbox": [ 334.66, 159.99, 33.18, 21.52 ], "instance_id": "", "name": "car" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the car on the left side of the person?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The car is below the traffic light." }
{ "answer": "The car is below the traffic light.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000370210.jpg", "index": "sealvqa_spatial_6", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the car to the left or right of the traffic light?" }, { "from": "gpt", "value": "The car is to the right of the traffic light." }, { "from": "human", "value": "Is the car above or below the traffic light?" }, { "from": "gpt", "value": "The car is below the traffic light." } ], "question": "Is the car above or below the traffic light?", "question_id": "sealvqa_spatial_6", "search": 1, "target_instances": [ { "bbox": [ 334.66, 159.99, 33.18, 21.52 ], "instance_id": "", "name": "car" }, { "bbox": [ 257.66, 80.96, 13.78, 22.04 ], "instance_id": "", "name": "traffic light" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the car above or below the traffic light?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the car is above the chair." }
{ "answer": "Yes, the car is above the chair.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000178939.jpg", "index": "sealvqa_spatial_7", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the car on the left side of the chair?" }, { "from": "gpt", "value": "No, the car is not on the left side of the chair." }, { "from": "human", "value": "Is the car above the chair?" }, { "from": "gpt", "value": "Yes, the car is above the chair." } ], "question": "Is the car above the chair?", "question_id": "sealvqa_spatial_7", "search": 1, "target_instances": [ { "bbox": [ 0.98, 257.78, 30.57, 140.63 ], "instance_id": "", "name": "chair" }, { "bbox": [ 138.11, 181.87, 29.32, 15.74 ], "instance_id": "", "name": "car" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the car above the chair?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The wine glass is above the knife." }
{ "answer": "The wine glass is above the knife.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000158497.jpg", "index": "sealvqa_spatial_8", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the knife on the left or right side of the wine glass?" }, { "from": "gpt", "value": "The knife is on the right side of the wine glass." }, { "from": "human", "value": "Is the wine glass above or below the knife?" }, { "from": "gpt", "value": "The wine glass is above the knife." } ], "question": "Is the wine glass above or below the knife?", "question_id": "sealvqa_spatial_8", "search": 1, "target_instances": [ { "bbox": [ 309.6, 163.21, 16.88, 21.59 ], "instance_id": "", "name": "knife" }, { "bbox": [ 257.58, 96.12, 24.5, 26.23 ], "instance_id": "", "name": "wine glass" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the wine glass above or below the knife?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The backpack is above the dog." }
{ "answer": "The backpack is above the dog.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000390348.jpg", "index": "sealvqa_spatial_9", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the backpack on the right side of the dog?" }, { "from": "gpt", "value": "No, the backpack is not on the right side of the dog." }, { "from": "human", "value": "Is the backpack above or below the dog?" }, { "from": "gpt", "value": "The backpack is above the dog." } ], "question": "Is the backpack above or below the dog?", "question_id": "sealvqa_spatial_9", "search": 1, "target_instances": [ { "bbox": [ 465.31, 216.49, 26.44, 46.16 ], "instance_id": "", "name": "dog" }, { "bbox": [ 170.58, 102.22, 39.98, 56.42 ], "instance_id": "", "name": "backpack" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the backpack above or below the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The person is above the dog." }
{ "answer": "The person is above the dog.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000047263.jpg", "index": "sealvqa_spatial_10", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the person to the left or right of the dog?" }, { "from": "gpt", "value": "The person is to the right of the dog." }, { "from": "human", "value": "Is the person above or below the dog?" }, { "from": "gpt", "value": "The person is above the dog." } ], "question": "Is the person above or below the dog?", "question_id": "sealvqa_spatial_10", "search": 1, "target_instances": [ { "bbox": [ 222.86, 186.51, 30.04, 41.67 ], "instance_id": "", "name": "dog" }, { "bbox": [ 344.44, 96, 29.49, 85.27 ], "instance_id": "", "name": "person" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the person above or below the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The dog is to the left of the bottle." }
{ "answer": "The dog is to the left of the bottle.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000519838.jpg", "index": "sealvqa_spatial_11", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the dog to the left or right of the bottle?" }, { "from": "gpt", "value": "The dog is to the left of the bottle." } ], "question": "Is the dog to the left or right of the bottle?", "question_id": "sealvqa_spatial_11", "search": 1, "target_instances": [ { "bbox": [ 55.29, 168.27, 70.63, 51.07 ], "instance_id": "", "name": "dog" }, { "bbox": [ 244.65, 190.11, 18.24, 27.63 ], "instance_id": "", "name": "bottle" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the dog to the left or right of the bottle?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the bottle is not to the left of the person." }
{ "answer": "No, the bottle is not to the left of the person.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000519838.jpg", "index": "sealvqa_spatial_12", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the bottle to the left of the person?" }, { "from": "gpt", "value": "No, the bottle is not to the left of the person." } ], "question": "Is the bottle to the left of the person?", "question_id": "sealvqa_spatial_12", "search": 1, "target_instances": [ { "bbox": [ 244.65, 190.11, 18.24, 27.63 ], "instance_id": "", "name": "bottle" }, { "bbox": [ 20.9, 86.97, 39.1, 125.39 ], "instance_id": "", "name": "person" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the bottle to the left of the person?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The dog is below the book." }
{ "answer": "The dog is below the book.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000151988.jpg", "index": "sealvqa_spatial_13", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the dog on the right side of the book?" }, { "from": "gpt", "value": "Yes, the dog is on the right side of the book." }, { "from": "human", "value": "Is the dog above or below the book?" }, { "from": "gpt", "value": "The dog is below the book." } ], "question": "Is the dog above or below the book?", "question_id": "sealvqa_spatial_13", "search": 1, "target_instances": [ { "bbox": [ 321.92, 292.11, 159.76, 55.71 ], "instance_id": "", "name": "dog" }, { "bbox": [ 275.61, 144.87, 21.36, 25.71 ], "instance_id": "", "name": "book" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the dog above or below the book?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the book is not below the bottle." }
{ "answer": "No, the book is not below the bottle.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000151988.jpg", "index": "sealvqa_spatial_14", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the bottle to the left or right of the book?" }, { "from": "gpt", "value": "The bottle is to the right of the book." }, { "from": "human", "value": "Is the book below the bottle?" }, { "from": "gpt", "value": "No, the book is not below the bottle." } ], "question": "Is the book below the bottle?", "question_id": "sealvqa_spatial_14", "search": 1, "target_instances": [ { "bbox": [ 381.02, 277.74, 25.12, 82.27 ], "instance_id": "", "name": "bottle" }, { "bbox": [ 275.61, 144.87, 21.36, 25.71 ], "instance_id": "", "name": "book" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the book below the bottle?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the dog is not above the traffic light." }
{ "answer": "No, the dog is not above the traffic light.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000205573.jpg", "index": "sealvqa_spatial_15", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the dog on the left side of the traffic light?" }, { "from": "gpt", "value": "Yes, the dog is on the left side of the traffic light." }, { "from": "human", "value": "Is the dog above the traffic light?" }, { "from": "gpt", "value": "No, the dog is not above the traffic light." } ], "question": "Is the dog above the traffic light?", "question_id": "sealvqa_spatial_15", "search": 1, "target_instances": [ { "bbox": [ 217.41, 159.26, 54.72, 44.77 ], "instance_id": "", "name": "dog" }, { "bbox": [ 468.48, 63.23, 22.3, 36.56 ], "instance_id": "", "name": "traffic light" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the dog above the traffic light?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the truck is above the dog." }
{ "answer": "Yes, the truck is above the dog.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000070815.jpg", "index": "sealvqa_spatial_16", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the truck to the left or right of the dog?" }, { "from": "gpt", "value": "The truck is to the left of the dog." }, { "from": "human", "value": "Is the truck above the dog?" }, { "from": "gpt", "value": "Yes, the truck is above the dog." } ], "question": "Is the truck above the dog?", "question_id": "sealvqa_spatial_16", "search": 1, "target_instances": [ { "bbox": [ 186.36, 269.28, 59.15, 97.85 ], "instance_id": "", "name": "dog" }, { "bbox": [ 0.39, 144.83, 64.79, 49.55 ], "instance_id": "", "name": "truck" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the truck above the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the apple is not below the oven." }
{ "answer": "No, the apple is not below the oven.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000057936.jpg", "index": "sealvqa_spatial_17", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the oven on the right side of the apple?" }, { "from": "gpt", "value": "Yes, the oven is on the right side of the apple." }, { "from": "human", "value": "Is the apple below the oven?" }, { "from": "gpt", "value": "No, the apple is not below the oven." } ], "question": "Is the apple below the oven?", "question_id": "sealvqa_spatial_17", "search": 1, "target_instances": [ { "bbox": [ 421.32, 81.38, 34.24, 154.84 ], "instance_id": "", "name": "oven" }, { "bbox": [ 190.15, 62.96, 9.16, 10.82 ], "instance_id": "", "name": "apple" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the apple below the oven?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The bottle is above the apple." }
{ "answer": "The bottle is above the apple.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000057936.jpg", "index": "sealvqa_spatial_18", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the bottle on the right side of the apple?" }, { "from": "gpt", "value": "Yes, the bottle is on the right side of the apple." }, { "from": "human", "value": "Is the bottle above or below the apple?" }, { "from": "gpt", "value": "The bottle is above the apple." } ], "question": "Is the bottle above or below the apple?", "question_id": "sealvqa_spatial_18", "search": 1, "target_instances": [ { "bbox": [ 421.12, 16.89, 10.46, 28.26 ], "instance_id": "", "name": "bottle" }, { "bbox": [ 190.15, 62.96, 9.16, 10.82 ], "instance_id": "", "name": "apple" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the bottle above or below the apple?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The dining table is below the cup." }
{ "answer": "The dining table is below the cup.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000560830.jpg", "index": "sealvqa_spatial_19", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the cup to the left of the dining table?" }, { "from": "gpt", "value": "Yes, the cup is to the left of the dining table." }, { "from": "human", "value": "Is the dining table above or below the cup?" }, { "from": "gpt", "value": "The dining table is below the cup." } ], "question": "Is the dining table above or below the cup?", "question_id": "sealvqa_spatial_19", "search": 1, "target_instances": [ { "bbox": [ 61.68, 186.99, 9.43, 8.28 ], "instance_id": "", "name": "cup" }, { "bbox": [ 200.68, 216.26, 80.68, 86.4 ], "instance_id": "", "name": "dining table" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the dining table above or below the cup?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The dog is to the left of the cell phone." }
{ "answer": "The dog is to the left of the cell phone.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000535483.jpg", "index": "sealvqa_spatial_20", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the dog to the left or right of the cell phone?" }, { "from": "gpt", "value": "The dog is to the left of the cell phone." } ], "question": "Is the dog to the left or right of the cell phone?", "question_id": "sealvqa_spatial_20", "search": 1, "target_instances": [ { "bbox": [ 236.2, 146.01, 26.17, 19.49 ], "instance_id": "", "name": "dog" }, { "bbox": [ 416.66, 138.71, 17.25, 21.87 ], "instance_id": "", "name": "cell phone" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the dog to the left or right of the cell phone?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The cell phone is above the bird." }
{ "answer": "The cell phone is above the bird.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000535483.jpg", "index": "sealvqa_spatial_21", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the cell phone on the left side of the bird?" }, { "from": "gpt", "value": "No, the cell phone is not on the left side of the bird." }, { "from": "human", "value": "Is the cell phone above or below the bird?" }, { "from": "gpt", "value": "The cell phone is above the bird." } ], "question": "Is the cell phone above or below the bird?", "question_id": "sealvqa_spatial_21", "search": 1, "target_instances": [ { "bbox": [ 16.25, 185.57, 16.21, 11.76 ], "instance_id": "", "name": "bird" }, { "bbox": [ 416.66, 138.71, 17.25, 21.87 ], "instance_id": "", "name": "cell phone" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the cell phone above or below the bird?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the bird is below the dog." }
{ "answer": "Yes, the bird is below the dog.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000535483.jpg", "index": "sealvqa_spatial_22", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the dog on the left side of the bird?" }, { "from": "gpt", "value": "No, the dog is not on the left side of the bird." }, { "from": "human", "value": "Is the bird below the dog?" }, { "from": "gpt", "value": "Yes, the bird is below the dog." } ], "question": "Is the bird below the dog?", "question_id": "sealvqa_spatial_22", "search": 1, "target_instances": [ { "bbox": [ 236.2, 146.01, 26.17, 19.49 ], "instance_id": "", "name": "dog" }, { "bbox": [ 16.25, 185.57, 16.21, 11.76 ], "instance_id": "", "name": "bird" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the bird below the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The truck is above the fire hydrant." }
{ "answer": "The truck is above the fire hydrant.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000187349.jpg", "index": "sealvqa_spatial_23", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the truck to the right of the fire hydrant?" }, { "from": "gpt", "value": "No, the truck is not to the right of the fire hydrant." }, { "from": "human", "value": "Is the truck above or below the fire hydrant?" }, { "from": "gpt", "value": "The truck is above the fire hydrant." } ], "question": "Is the truck above or below the fire hydrant?", "question_id": "sealvqa_spatial_23", "search": 1, "target_instances": [ { "bbox": [ 558.09, 431.71, 4.78, 7.31 ], "instance_id": "", "name": "fire hydrant" }, { "bbox": [ 259.17, 73.32, 71.71, 51.58 ], "instance_id": "", "name": "truck" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the truck above or below the fire hydrant?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the truck is above the stop sign." }
{ "answer": "Yes, the truck is above the stop sign.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000187349.jpg", "index": "sealvqa_spatial_24", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the truck to the left of the stop sign?" }, { "from": "gpt", "value": "Yes, the truck is to the left of the stop sign." }, { "from": "human", "value": "Is the truck above the stop sign?" }, { "from": "gpt", "value": "Yes, the truck is above the stop sign." } ], "question": "Is the truck above the stop sign?", "question_id": "sealvqa_spatial_24", "search": 1, "target_instances": [ { "bbox": [ 445.65, 424.39, 5.51, 8.09 ], "instance_id": "", "name": "stop sign" }, { "bbox": [ 259.17, 73.32, 71.71, 51.58 ], "instance_id": "", "name": "truck" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the truck above the stop sign?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the fire hydrant is not to the left of the stop sign." }
{ "answer": "No, the fire hydrant is not to the left of the stop sign.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000187349.jpg", "index": "sealvqa_spatial_25", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the fire hydrant to the left of the stop sign?" }, { "from": "gpt", "value": "No, the fire hydrant is not to the left of the stop sign." } ], "question": "Is the fire hydrant to the left of the stop sign?", "question_id": "sealvqa_spatial_25", "search": 1, "target_instances": [ { "bbox": [ 558.09, 431.71, 4.78, 7.31 ], "instance_id": "", "name": "fire hydrant" }, { "bbox": [ 445.65, 424.39, 5.51, 8.09 ], "instance_id": "", "name": "stop sign" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the fire hydrant to the left of the stop sign?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The sink is on the right side of the bottle." }
{ "answer": "The sink is on the right side of the bottle.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000282134.jpg", "index": "sealvqa_spatial_26", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the sink on the left or right side of the bottle?" }, { "from": "gpt", "value": "The sink is on the right side of the bottle." } ], "question": "Is the sink on the left or right side of the bottle?", "question_id": "sealvqa_spatial_26", "search": 1, "target_instances": [ { "bbox": [ 336.37, 24.12, 21.29, 68.24 ], "instance_id": "", "name": "bottle" }, { "bbox": [ 534.05, 71.74, 104.79, 20.71 ], "instance_id": "", "name": "sink" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the sink on the left or right side of the bottle?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The bottle is below the dog." }
{ "answer": "The bottle is below the dog.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000007125.jpg", "index": "sealvqa_spatial_27", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the dog to the left or right of the bottle?" }, { "from": "gpt", "value": "The dog is to the right of the bottle." }, { "from": "human", "value": "Is the bottle above or below the dog?" }, { "from": "gpt", "value": "The bottle is below the dog." } ], "question": "Is the bottle above or below the dog?", "question_id": "sealvqa_spatial_27", "search": 1, "target_instances": [ { "bbox": [ 377.68, 258.81, 13.28, 9.36 ], "instance_id": "", "name": "dog" }, { "bbox": [ 69.83, 359.86, 18.24, 24.95 ], "instance_id": "", "name": "bottle" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the bottle above or below the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the bottle is not above the backpack." }
{ "answer": "No, the bottle is not above the backpack.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000007125.jpg", "index": "sealvqa_spatial_28", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the backpack to the left or right of the bottle?" }, { "from": "gpt", "value": "The backpack is to the right of the bottle." }, { "from": "human", "value": "Is the bottle above the backpack?" }, { "from": "gpt", "value": "No, the bottle is not above the backpack." } ], "question": "Is the bottle above the backpack?", "question_id": "sealvqa_spatial_28", "search": 1, "target_instances": [ { "bbox": [ 69.83, 359.86, 18.24, 24.95 ], "instance_id": "", "name": "bottle" }, { "bbox": [ 88.45, 255.88, 27.06, 48.02 ], "instance_id": "", "name": "backpack" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the bottle above the backpack?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The dog is to the right of the backpack." }
{ "answer": "The dog is to the right of the backpack.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000007125.jpg", "index": "sealvqa_spatial_29", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the dog to the left or right of the backpack?" }, { "from": "gpt", "value": "The dog is to the right of the backpack." } ], "question": "Is the dog to the left or right of the backpack?", "question_id": "sealvqa_spatial_29", "search": 1, "target_instances": [ { "bbox": [ 377.68, 258.81, 13.28, 9.36 ], "instance_id": "", "name": "dog" }, { "bbox": [ 88.45, 255.88, 27.06, 48.02 ], "instance_id": "", "name": "backpack" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the dog to the left or right of the backpack?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the handbag is on the right side of the dog." }
{ "answer": "Yes, the handbag is on the right side of the dog.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000386165.jpg", "index": "sealvqa_spatial_30", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the handbag on the right side of the dog?" }, { "from": "gpt", "value": "Yes, the handbag is on the right side of the dog." } ], "question": "Is the handbag on the right side of the dog?", "question_id": "sealvqa_spatial_30", "search": 1, "target_instances": [ { "bbox": [ 161.51, 290.24, 79.88, 84.08 ], "instance_id": "", "name": "dog" }, { "bbox": [ 286.14, 199.76, 55.61, 116.69 ], "instance_id": "", "name": "handbag" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the handbag on the right side of the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The stop sign is above the person." }
{ "answer": "The stop sign is above the person.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000559950.jpg", "index": "sealvqa_spatial_31", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the person on the right side of the stop sign?" }, { "from": "gpt", "value": "Yes, the person is on the right side of the stop sign." }, { "from": "human", "value": "Is the stop sign above or below the person?" }, { "from": "gpt", "value": "The stop sign is above the person." } ], "question": "Is the stop sign above or below the person?", "question_id": "sealvqa_spatial_31", "search": 1, "target_instances": [ { "bbox": [ 252.39, 326.51, 17.12, 45.78 ], "instance_id": "", "name": "person" }, { "bbox": [ 106.5, 280.62, 21.67, 22.01 ], "instance_id": "", "name": "stop sign" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the stop sign above or below the person?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the clock is not on the left side of the bottle." }
{ "answer": "No, the clock is not on the left side of the bottle.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000020671.jpg", "index": "sealvqa_spatial_32", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the clock on the left side of the bottle?" }, { "from": "gpt", "value": "No, the clock is not on the left side of the bottle." } ], "question": "Is the clock on the left side of the bottle?", "question_id": "sealvqa_spatial_32", "search": 1, "target_instances": [ { "bbox": [ 384.69, 252.2, 18, 16.65 ], "instance_id": "", "name": "clock" }, { "bbox": [ 341.19, 228.58, 38.08, 89.17 ], "instance_id": "", "name": "bottle" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the clock on the left side of the bottle?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The dog is to the left of the person." }
{ "answer": "The dog is to the left of the person.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000278550.jpg", "index": "sealvqa_spatial_33", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the dog to the left or right of the person?" }, { "from": "gpt", "value": "The dog is to the left of the person." } ], "question": "Is the dog to the left or right of the person?", "question_id": "sealvqa_spatial_33", "search": 1, "target_instances": [ { "bbox": [ 12.47, 82.61, 107.86, 62.35 ], "instance_id": "", "name": "dog" }, { "bbox": [ 294.44, 142.48, 16.35, 22.69 ], "instance_id": "", "name": "person" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the dog to the left or right of the person?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the oven is not above the cup." }
{ "answer": "No, the oven is not above the cup.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000209468.jpg", "index": "sealvqa_spatial_34", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the cup to the left or right of the oven?" }, { "from": "gpt", "value": "The cup is to the left of the oven." }, { "from": "human", "value": "Is the oven above the cup?" }, { "from": "gpt", "value": "No, the oven is not above the cup." } ], "question": "Is the oven above the cup?", "question_id": "sealvqa_spatial_34", "search": 1, "target_instances": [ { "bbox": [ 255.07, 303.44, 64.57, 117.31 ], "instance_id": "", "name": "oven" }, { "bbox": [ 162.88, 255.29, 18.17, 23.61 ], "instance_id": "", "name": "cup" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the oven above the cup?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The bowl is on the left side of the laptop." }
{ "answer": "The bowl is on the left side of the laptop.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000209468.jpg", "index": "sealvqa_spatial_35", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the bowl on the left or right side of the laptop?" }, { "from": "gpt", "value": "The bowl is on the left side of the laptop." } ], "question": "Is the bowl on the left or right side of the laptop?", "question_id": "sealvqa_spatial_35", "search": 1, "target_instances": [ { "bbox": [ 268.58, 222.2, 88.45, 65.8 ], "instance_id": "", "name": "laptop" }, { "bbox": [ 136.12, 262.21, 26.33, 12.08 ], "instance_id": "", "name": "bowl" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the bowl on the left or right side of the laptop?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The cup is on the left side of the microwave." }
{ "answer": "The cup is on the left side of the microwave.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000210012.jpg", "index": "sealvqa_spatial_36", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the cup on the left or right side of the microwave?" }, { "from": "gpt", "value": "The cup is on the left side of the microwave." } ], "question": "Is the cup on the left or right side of the microwave?", "question_id": "sealvqa_spatial_36", "search": 1, "target_instances": [ { "bbox": [ 354.88, 107.87, 66.87, 33.43 ], "instance_id": "", "name": "microwave" }, { "bbox": [ 125.6, 131.24, 13.8, 14.13 ], "instance_id": "", "name": "cup" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the cup on the left or right side of the microwave?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the cup is above the dog." }
{ "answer": "Yes, the cup is above the dog.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000210012.jpg", "index": "sealvqa_spatial_37", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the cup to the right of the dog?" }, { "from": "gpt", "value": "No, the cup is not to the right of the dog." }, { "from": "human", "value": "Is the cup above the dog?" }, { "from": "gpt", "value": "Yes, the cup is above the dog." } ], "question": "Is the cup above the dog?", "question_id": "sealvqa_spatial_37", "search": 1, "target_instances": [ { "bbox": [ 314.29, 209, 89.38, 71.19 ], "instance_id": "", "name": "dog" }, { "bbox": [ 125.6, 131.24, 13.8, 14.13 ], "instance_id": "", "name": "cup" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the cup above the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the surfboard is not to the right of the dog." }
{ "answer": "No, the surfboard is not to the right of the dog.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000272153.jpg", "index": "sealvqa_spatial_38", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the surfboard to the right of the dog?" }, { "from": "gpt", "value": "No, the surfboard is not to the right of the dog." } ], "question": "Is the surfboard to the right of the dog?", "question_id": "sealvqa_spatial_38", "search": 1, "target_instances": [ { "bbox": [ 261.04, 293.65, 100.2, 97.49 ], "instance_id": "", "name": "dog" }, { "bbox": [ 134.51, 183.08, 55.44, 146.28 ], "instance_id": "", "name": "surfboard" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the surfboard to the right of the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The clock is above the handbag." }
{ "answer": "The clock is above the handbag.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000386968.jpg", "index": "sealvqa_spatial_39", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the handbag to the right of the clock?" }, { "from": "gpt", "value": "Yes, the handbag is to the right of the clock." }, { "from": "human", "value": "Is the clock above or below the handbag?" }, { "from": "gpt", "value": "The clock is above the handbag." } ], "question": "Is the clock above or below the handbag?", "question_id": "sealvqa_spatial_39", "search": 1, "target_instances": [ { "bbox": [ 432.26, 204.98, 70.98, 88.61 ], "instance_id": "", "name": "handbag" }, { "bbox": [ 187.27, 24.83, 15.3, 20.6 ], "instance_id": "", "name": "clock" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the clock above or below the handbag?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the dog is not above the backpack." }
{ "answer": "No, the dog is not above the backpack.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000210060.jpg", "index": "sealvqa_spatial_40", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the dog to the left or right of the backpack?" }, { "from": "gpt", "value": "The dog is to the right of the backpack." }, { "from": "human", "value": "Is the dog above the backpack?" }, { "from": "gpt", "value": "No, the dog is not above the backpack." } ], "question": "Is the dog above the backpack?", "question_id": "sealvqa_spatial_40", "search": 1, "target_instances": [ { "bbox": [ 388.18, 222.56, 57.8, 150.09 ], "instance_id": "", "name": "dog" }, { "bbox": [ 254.3, 120.08, 42.46, 45.73 ], "instance_id": "", "name": "backpack" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the dog above the backpack?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The person is above the dog." }
{ "answer": "The person is above the dog.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000106166.jpg", "index": "sealvqa_spatial_41", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the person on the left or right side of the dog?" }, { "from": "gpt", "value": "The person is on the left side of the dog." }, { "from": "human", "value": "Is the person above or below the dog?" }, { "from": "gpt", "value": "The person is above the dog." } ], "question": "Is the person above or below the dog?", "question_id": "sealvqa_spatial_41", "search": 1, "target_instances": [ { "bbox": [ 372.2, 205.54, 76.05, 82.66 ], "instance_id": "", "name": "dog" }, { "bbox": [ 160.15, 145.02, 27.73, 28.7 ], "instance_id": "", "name": "person" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the person above or below the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the motorcycle is to the left of the chair." }
{ "answer": "Yes, the motorcycle is to the left of the chair.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000276719.jpg", "index": "sealvqa_spatial_42", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the motorcycle to the left of the chair?" }, { "from": "gpt", "value": "Yes, the motorcycle is to the left of the chair." } ], "question": "Is the motorcycle to the left of the chair?", "question_id": "sealvqa_spatial_42", "search": 1, "target_instances": [ { "bbox": [ 365.68, 120.52, 30.54, 53.37 ], "instance_id": "", "name": "chair" }, { "bbox": [ 272.7, 73.86, 44.73, 56.14 ], "instance_id": "", "name": "motorcycle" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the motorcycle to the left of the chair?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the dog is to the left of the person." }
{ "answer": "Yes, the dog is to the left of the person.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000444576.jpg", "index": "sealvqa_spatial_43", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the dog to the left of the person?" }, { "from": "gpt", "value": "Yes, the dog is to the left of the person." } ], "question": "Is the dog to the left of the person?", "question_id": "sealvqa_spatial_43", "search": 1, "target_instances": [ { "bbox": [ 280.51, 178.63, 37.91, 45.84 ], "instance_id": "", "name": "dog" }, { "bbox": [ 324.27, 190.57, 25.83, 35.52 ], "instance_id": "", "name": "person" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the dog to the left of the person?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the handbag is above the dog." }
{ "answer": "Yes, the handbag is above the dog.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000319055.jpg", "index": "sealvqa_spatial_44", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the handbag to the left of the dog?" }, { "from": "gpt", "value": "Yes, the handbag is to the left of the dog." }, { "from": "human", "value": "Is the handbag above the dog?" }, { "from": "gpt", "value": "Yes, the handbag is above the dog." } ], "question": "Is the handbag above the dog?", "question_id": "sealvqa_spatial_44", "search": 1, "target_instances": [ { "bbox": [ 484.33, 224.38, 34.03, 22.54 ], "instance_id": "", "name": "dog" }, { "bbox": [ 465.89, 215.5, 5.96, 5.28 ], "instance_id": "", "name": "handbag" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the handbag above the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the dog is on the right side of the car." }
{ "answer": "Yes, the dog is on the right side of the car.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000027519.jpg", "index": "sealvqa_spatial_45", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the dog on the right side of the car?" }, { "from": "gpt", "value": "Yes, the dog is on the right side of the car." } ], "question": "Is the dog on the right side of the car?", "question_id": "sealvqa_spatial_45", "search": 1, "target_instances": [ { "bbox": [ 237.1, 375.1, 62.9, 81.29 ], "instance_id": "", "name": "dog" }, { "bbox": [ 111.8, 269.47, 40.56, 115.67 ], "instance_id": "", "name": "car" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the dog on the right side of the car?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the bowl is to the left of the dog." }
{ "answer": "Yes, the bowl is to the left of the dog.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000346560.jpg", "index": "sealvqa_spatial_46", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the bowl to the left of the dog?" }, { "from": "gpt", "value": "Yes, the bowl is to the left of the dog." } ], "question": "Is the bowl to the left of the dog?", "question_id": "sealvqa_spatial_46", "search": 1, "target_instances": [ { "bbox": [ 547.36, 238.72, 56.67, 121.77 ], "instance_id": "", "name": "dog" }, { "bbox": [ 6.81, 249.02, 75.77, 46.92 ], "instance_id": "", "name": "bowl" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the bowl to the left of the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The handbag is below the backpack." }
{ "answer": "The handbag is below the backpack.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000018783.jpg", "index": "sealvqa_spatial_47", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the handbag to the left of the backpack?" }, { "from": "gpt", "value": "No, the handbag is not to the left of the backpack." }, { "from": "human", "value": "Is the handbag above or below the backpack?" }, { "from": "gpt", "value": "The handbag is below the backpack." } ], "question": "Is the handbag above or below the backpack?", "question_id": "sealvqa_spatial_47", "search": 1, "target_instances": [ { "bbox": [ 246.88, 190.25, 82.78, 90.56 ], "instance_id": "", "name": "backpack" }, { "bbox": [ 361.97, 361.05, 65.54, 71.49 ], "instance_id": "", "name": "handbag" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the handbag above or below the backpack?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the backpack is on the left side of the car." }
{ "answer": "Yes, the backpack is on the left side of the car.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000018783.jpg", "index": "sealvqa_spatial_48", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the backpack on the left side of the car?" }, { "from": "gpt", "value": "Yes, the backpack is on the left side of the car." } ], "question": "Is the backpack on the left side of the car?", "question_id": "sealvqa_spatial_48", "search": 1, "target_instances": [ { "bbox": [ 612.18, 269.8, 27.48, 100.29 ], "instance_id": "", "name": "car" }, { "bbox": [ 246.88, 190.25, 82.78, 90.56 ], "instance_id": "", "name": "backpack" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the backpack on the left side of the car?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the handbag is to the left of the car." }
{ "answer": "Yes, the handbag is to the left of the car.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000018783.jpg", "index": "sealvqa_spatial_49", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the handbag to the left of the car?" }, { "from": "gpt", "value": "Yes, the handbag is to the left of the car." } ], "question": "Is the handbag to the left of the car?", "question_id": "sealvqa_spatial_49", "search": 1, "target_instances": [ { "bbox": [ 612.18, 269.8, 27.48, 100.29 ], "instance_id": "", "name": "car" }, { "bbox": [ 361.97, 361.05, 65.54, 71.49 ], "instance_id": "", "name": "handbag" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the handbag to the left of the car?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the microwave is above the bottle." }
{ "answer": "Yes, the microwave is above the bottle.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000206784.jpg", "index": "sealvqa_spatial_50", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the bottle on the left side of the microwave?" }, { "from": "gpt", "value": "No, the bottle is not on the left side of the microwave." }, { "from": "human", "value": "Is the microwave above the bottle?" }, { "from": "gpt", "value": "Yes, the microwave is above the bottle." } ], "question": "Is the microwave above the bottle?", "question_id": "sealvqa_spatial_50", "search": 1, "target_instances": [ { "bbox": [ 570.95, 302.58, 22.77, 56.21 ], "instance_id": "", "name": "bottle" }, { "bbox": [ 445.12, 237.04, 67.49, 41.19 ], "instance_id": "", "name": "microwave" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the microwave above the bottle?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The bottle is below the clock." }
{ "answer": "The bottle is below the clock.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000206784.jpg", "index": "sealvqa_spatial_51", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the bottle to the left of the clock?" }, { "from": "gpt", "value": "No, the bottle is not to the left of the clock." }, { "from": "human", "value": "Is the bottle above or below the clock?" }, { "from": "gpt", "value": "The bottle is below the clock." } ], "question": "Is the bottle above or below the clock?", "question_id": "sealvqa_spatial_51", "search": 1, "target_instances": [ { "bbox": [ 570.95, 302.58, 22.77, 56.21 ], "instance_id": "", "name": "bottle" }, { "bbox": [ 430.21, 203.48, 19.05, 16.12 ], "instance_id": "", "name": "clock" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the bottle above or below the clock?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The sink is above the bottle." }
{ "answer": "The sink is above the bottle.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000206784.jpg", "index": "sealvqa_spatial_52", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the bottle to the right of the sink?" }, { "from": "gpt", "value": "Yes, the bottle is to the right of the sink." }, { "from": "human", "value": "Is the sink above or below the bottle?" }, { "from": "gpt", "value": "The sink is above the bottle." } ], "question": "Is the sink above or below the bottle?", "question_id": "sealvqa_spatial_52", "search": 1, "target_instances": [ { "bbox": [ 570.95, 302.58, 22.77, 56.21 ], "instance_id": "", "name": "bottle" }, { "bbox": [ 366.21, 254.72, 59.79, 34.39 ], "instance_id": "", "name": "sink" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the sink above or below the bottle?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The vase is above the toilet." }
{ "answer": "The vase is above the toilet.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000221869.jpg", "index": "sealvqa_spatial_53", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the toilet to the left or right of the vase?" }, { "from": "gpt", "value": "The toilet is to the left of the vase." }, { "from": "human", "value": "Is the vase above or below the toilet?" }, { "from": "gpt", "value": "The vase is above the toilet." } ], "question": "Is the vase above or below the toilet?", "question_id": "sealvqa_spatial_53", "search": 1, "target_instances": [ { "bbox": [ 123.27, 339.37, 7.72, 26.72 ], "instance_id": "", "name": "toilet" }, { "bbox": [ 215.94, 246.11, 58.73, 48.4 ], "instance_id": "", "name": "vase" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the vase above or below the toilet?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the sink is not above the clock." }
{ "answer": "No, the sink is not above the clock.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000022621.jpg", "index": "sealvqa_spatial_54", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the sink to the left of the clock?" }, { "from": "gpt", "value": "Yes, the sink is to the left of the clock." }, { "from": "human", "value": "Is the sink above the clock?" }, { "from": "gpt", "value": "No, the sink is not above the clock." } ], "question": "Is the sink above the clock?", "question_id": "sealvqa_spatial_54", "search": 1, "target_instances": [ { "bbox": [ 115.06, 290.52, 159.64, 31.64 ], "instance_id": "", "name": "sink" }, { "bbox": [ 410.7, 201.86, 10.3, 15.77 ], "instance_id": "", "name": "clock" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the sink above the clock?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the cup is not above the sink." }
{ "answer": "No, the cup is not above the sink.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000078260.jpg", "index": "sealvqa_spatial_55", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the sink on the left side of the cup?" }, { "from": "gpt", "value": "No, the sink is not on the left side of the cup." }, { "from": "human", "value": "Is the cup above the sink?" }, { "from": "gpt", "value": "No, the cup is not above the sink." } ], "question": "Is the cup above the sink?", "question_id": "sealvqa_spatial_55", "search": 1, "target_instances": [ { "bbox": [ 185.62, 249.99, 25.36, 27.7 ], "instance_id": "", "name": "cup" }, { "bbox": [ 365.2, 222.19, 34.13, 7.1 ], "instance_id": "", "name": "sink" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the cup above the sink?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the microwave is on the right side of the bottle." }
{ "answer": "Yes, the microwave is on the right side of the bottle.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000078260.jpg", "index": "sealvqa_spatial_56", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the microwave on the right side of the bottle?" }, { "from": "gpt", "value": "Yes, the microwave is on the right side of the bottle." } ], "question": "Is the microwave on the right side of the bottle?", "question_id": "sealvqa_spatial_56", "search": 1, "target_instances": [ { "bbox": [ 160.65, 182.84, 10.11, 32.86 ], "instance_id": "", "name": "bottle" }, { "bbox": [ 200.19, 179.2, 56.36, 32.39 ], "instance_id": "", "name": "microwave" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the microwave on the right side of the bottle?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the oven is not below the cup." }
{ "answer": "No, the oven is not below the cup.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000128201.jpg", "index": "sealvqa_spatial_57", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the oven to the left of the cup?" }, { "from": "gpt", "value": "No, the oven is not to the left of the cup." }, { "from": "human", "value": "Is the oven below the cup?" }, { "from": "gpt", "value": "No, the oven is not below the cup." } ], "question": "Is the oven below the cup?", "question_id": "sealvqa_spatial_57", "search": 1, "target_instances": [ { "bbox": [ 173.88, 294.11, 14.22, 18.44 ], "instance_id": "", "name": "cup" }, { "bbox": [ 428.93, 130.95, 55.6, 63.42 ], "instance_id": "", "name": "oven" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the oven below the cup?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The oven is below the cup." }
{ "answer": "The oven is below the cup.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000092998.jpg", "index": "sealvqa_spatial_58", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the oven to the left or right of the cup?" }, { "from": "gpt", "value": "The oven is to the right of the cup." }, { "from": "human", "value": "Is the oven above or below the cup?" }, { "from": "gpt", "value": "The oven is below the cup." } ], "question": "Is the oven above or below the cup?", "question_id": "sealvqa_spatial_58", "search": 1, "target_instances": [ { "bbox": [ 239.26, 142.58, 15.99, 19.19 ], "instance_id": "", "name": "cup" }, { "bbox": [ 376.22, 232.43, 37.83, 105.95 ], "instance_id": "", "name": "oven" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the oven above or below the cup?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The cup is above the orange." }
{ "answer": "The cup is above the orange.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000092998.jpg", "index": "sealvqa_spatial_59", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the orange on the left or right side of the cup?" }, { "from": "gpt", "value": "The orange is on the left side of the cup." }, { "from": "human", "value": "Is the cup above or below the orange?" }, { "from": "gpt", "value": "The cup is above the orange." } ], "question": "Is the cup above or below the orange?", "question_id": "sealvqa_spatial_59", "search": 1, "target_instances": [ { "bbox": [ 239.26, 142.58, 15.99, 19.19 ], "instance_id": "", "name": "cup" }, { "bbox": [ 185.5, 259.23, 9.58, 11.25 ], "instance_id": "", "name": "orange" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the cup above or below the orange?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the oven is on the right side of the orange." }
{ "answer": "Yes, the oven is on the right side of the orange.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000092998.jpg", "index": "sealvqa_spatial_60", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the oven on the right side of the orange?" }, { "from": "gpt", "value": "Yes, the oven is on the right side of the orange." } ], "question": "Is the oven on the right side of the orange?", "question_id": "sealvqa_spatial_60", "search": 1, "target_instances": [ { "bbox": [ 185.5, 259.23, 9.58, 11.25 ], "instance_id": "", "name": "orange" }, { "bbox": [ 376.22, 232.43, 37.83, 105.95 ], "instance_id": "", "name": "oven" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the oven on the right side of the orange?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The chair is below the sink." }
{ "answer": "The chair is below the sink.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000093959.jpg", "index": "sealvqa_spatial_61", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the chair on the left side of the sink?" }, { "from": "gpt", "value": "No, the chair is not on the left side of the sink." }, { "from": "human", "value": "Is the chair above or below the sink?" }, { "from": "gpt", "value": "The chair is below the sink." } ], "question": "Is the chair above or below the sink?", "question_id": "sealvqa_spatial_61", "search": 1, "target_instances": [ { "bbox": [ 116.37, 313.13, 169.27, 31.53 ], "instance_id": "", "name": "sink" }, { "bbox": [ 397.37, 563.14, 79.93, 76.86 ], "instance_id": "", "name": "chair" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the chair above or below the sink?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the sink is not to the right of the toaster." }
{ "answer": "No, the sink is not to the right of the toaster.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000093959.jpg", "index": "sealvqa_spatial_62", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the sink to the right of the toaster?" }, { "from": "gpt", "value": "No, the sink is not to the right of the toaster." } ], "question": "Is the sink to the right of the toaster?", "question_id": "sealvqa_spatial_62", "search": 1, "target_instances": [ { "bbox": [ 381.31, 329.13, 58.51, 57.83 ], "instance_id": "", "name": "toaster" }, { "bbox": [ 116.37, 313.13, 169.27, 31.53 ], "instance_id": "", "name": "sink" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the sink to the right of the toaster?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the bowl is on the right side of the wine glass." }
{ "answer": "Yes, the bowl is on the right side of the wine glass.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000077102.jpg", "index": "sealvqa_spatial_63", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the bowl on the right side of the wine glass?" }, { "from": "gpt", "value": "Yes, the bowl is on the right side of the wine glass." } ], "question": "Is the bowl on the right side of the wine glass?", "question_id": "sealvqa_spatial_63", "search": 1, "target_instances": [ { "bbox": [ 82.95, 293.52, 82.28, 30.66 ], "instance_id": "", "name": "bowl" }, { "bbox": [ 39.48, 260.01, 31.08, 62.5 ], "instance_id": "", "name": "wine glass" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the bowl on the right side of the wine glass?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The wine glass is below the bottle." }
{ "answer": "The wine glass is below the bottle.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000077102.jpg", "index": "sealvqa_spatial_64", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the wine glass on the left side of the bottle?" }, { "from": "gpt", "value": "Yes, the wine glass is on the left side of the bottle." }, { "from": "human", "value": "Is the wine glass above or below the bottle?" }, { "from": "gpt", "value": "The wine glass is below the bottle." } ], "question": "Is the wine glass above or below the bottle?", "question_id": "sealvqa_spatial_64", "search": 1, "target_instances": [ { "bbox": [ 73.55, 177.5, 26.9, 81.43 ], "instance_id": "", "name": "bottle" }, { "bbox": [ 39.48, 260.01, 31.08, 62.5 ], "instance_id": "", "name": "wine glass" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the wine glass above or below the bottle?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the bottle is not above the scissors." }
{ "answer": "No, the bottle is not above the scissors.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000087567.jpg", "index": "sealvqa_spatial_65", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the scissors on the left or right side of the bottle?" }, { "from": "gpt", "value": "The scissors is on the right side of the bottle." }, { "from": "human", "value": "Is the bottle above the scissors?" }, { "from": "gpt", "value": "No, the bottle is not above the scissors." } ], "question": "Is the bottle above the scissors?", "question_id": "sealvqa_spatial_65", "search": 1, "target_instances": [ { "bbox": [ 261.59, 159.02, 11.9, 45.68 ], "instance_id": "", "name": "scissors" }, { "bbox": [ 9.71, 212.13, 55.48, 40.56 ], "instance_id": "", "name": "bottle" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the bottle above the scissors?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The oven is below the wine glass." }
{ "answer": "The oven is below the wine glass.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000293611.jpg", "index": "sealvqa_spatial_66", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the wine glass on the right side of the oven?" }, { "from": "gpt", "value": "Yes, the wine glass is on the right side of the oven." }, { "from": "human", "value": "Is the oven above or below the wine glass?" }, { "from": "gpt", "value": "The oven is below the wine glass." } ], "question": "Is the oven above or below the wine glass?", "question_id": "sealvqa_spatial_66", "search": 1, "target_instances": [ { "bbox": [ 0, 312.95, 41.26, 103.77 ], "instance_id": "", "name": "oven" }, { "bbox": [ 338.67, 228.47, 30.89, 20.17 ], "instance_id": "", "name": "wine glass" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the oven above or below the wine glass?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the potted plant is not below the wine glass." }
{ "answer": "No, the potted plant is not below the wine glass.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000293611.jpg", "index": "sealvqa_spatial_67", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the potted plant to the left or right of the wine glass?" }, { "from": "gpt", "value": "The potted plant is to the left of the wine glass." }, { "from": "human", "value": "Is the potted plant below the wine glass?" }, { "from": "gpt", "value": "No, the potted plant is not below the wine glass." } ], "question": "Is the potted plant below the wine glass?", "question_id": "sealvqa_spatial_67", "search": 1, "target_instances": [ { "bbox": [ 293.71, 96.17, 36.62, 50.3 ], "instance_id": "", "name": "potted plant" }, { "bbox": [ 338.67, 228.47, 30.89, 20.17 ], "instance_id": "", "name": "wine glass" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the potted plant below the wine glass?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the oven is below the potted plant." }
{ "answer": "Yes, the oven is below the potted plant.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000293611.jpg", "index": "sealvqa_spatial_68", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the oven to the right of the potted plant?" }, { "from": "gpt", "value": "No, the oven is not to the right of the potted plant." }, { "from": "human", "value": "Is the oven below the potted plant?" }, { "from": "gpt", "value": "Yes, the oven is below the potted plant." } ], "question": "Is the oven below the potted plant?", "question_id": "sealvqa_spatial_68", "search": 1, "target_instances": [ { "bbox": [ 293.71, 96.17, 36.62, 50.3 ], "instance_id": "", "name": "potted plant" }, { "bbox": [ 0, 312.95, 41.26, 103.77 ], "instance_id": "", "name": "oven" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the oven below the potted plant?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the potted plant is below the orange." }
{ "answer": "Yes, the potted plant is below the orange.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000107516.jpg", "index": "sealvqa_spatial_69", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the potted plant on the left or right side of the orange?" }, { "from": "gpt", "value": "The potted plant is on the right side of the orange." }, { "from": "human", "value": "Is the potted plant below the orange?" }, { "from": "gpt", "value": "Yes, the potted plant is below the orange." } ], "question": "Is the potted plant below the orange?", "question_id": "sealvqa_spatial_69", "search": 1, "target_instances": [ { "bbox": [ 290.6, 315.52, 34.97, 42.94 ], "instance_id": "", "name": "potted plant" }, { "bbox": [ 134.79, 278.62, 31.51, 9.43 ], "instance_id": "", "name": "orange" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the potted plant below the orange?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The sink is below the potted plant." }
{ "answer": "The sink is below the potted plant.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000107516.jpg", "index": "sealvqa_spatial_70", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the sink on the left or right side of the potted plant?" }, { "from": "gpt", "value": "The sink is on the left side of the potted plant." }, { "from": "human", "value": "Is the sink above or below the potted plant?" }, { "from": "gpt", "value": "The sink is below the potted plant." } ], "question": "Is the sink above or below the potted plant?", "question_id": "sealvqa_spatial_70", "search": 1, "target_instances": [ { "bbox": [ 290.6, 315.52, 34.97, 42.94 ], "instance_id": "", "name": "potted plant" }, { "bbox": [ 118.87, 403.14, 130.62, 40.82 ], "instance_id": "", "name": "sink" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the sink above or below the potted plant?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the sink is not below the vase." }
{ "answer": "No, the sink is not below the vase.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000200116.jpg", "index": "sealvqa_spatial_71", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the vase to the right of the sink?" }, { "from": "gpt", "value": "Yes, the vase is to the right of the sink." }, { "from": "human", "value": "Is the sink below the vase?" }, { "from": "gpt", "value": "No, the sink is not below the vase." } ], "question": "Is the sink below the vase?", "question_id": "sealvqa_spatial_71", "search": 1, "target_instances": [ { "bbox": [ 539.36, 335.73, 39.57, 47.02 ], "instance_id": "", "name": "vase" }, { "bbox": [ 227.25, 234.09, 51.91, 9.68 ], "instance_id": "", "name": "sink" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the sink below the vase?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the sink is below the microwave." }
{ "answer": "Yes, the sink is below the microwave.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000331268.jpg", "index": "sealvqa_spatial_72", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the sink on the right side of the microwave?" }, { "from": "gpt", "value": "Yes, the sink is on the right side of the microwave." }, { "from": "human", "value": "Is the sink below the microwave?" }, { "from": "gpt", "value": "Yes, the sink is below the microwave." } ], "question": "Is the sink below the microwave?", "question_id": "sealvqa_spatial_72", "search": 1, "target_instances": [ { "bbox": [ 442.06, 282.11, 161.98, 53.06 ], "instance_id": "", "name": "sink" }, { "bbox": [ 25.03, 231.79, 108.73, 35.68 ], "instance_id": "", "name": "microwave" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the sink below the microwave?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The oven is to the right of the microwave." }
{ "answer": "The oven is to the right of the microwave.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000104326.jpg", "index": "sealvqa_spatial_73", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the oven to the left or right of the microwave?" }, { "from": "gpt", "value": "The oven is to the right of the microwave." } ], "question": "Is the oven to the left or right of the microwave?", "question_id": "sealvqa_spatial_73", "search": 1, "target_instances": [ { "bbox": [ 0.24, 293.05, 22.33, 52.57 ], "instance_id": "", "name": "microwave" }, { "bbox": [ 145.43, 274.54, 59.88, 84.84 ], "instance_id": "", "name": "oven" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the oven to the left or right of the microwave?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the clock is not below the oven." }
{ "answer": "No, the clock is not below the oven.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000104326.jpg", "index": "sealvqa_spatial_74", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the clock to the left of the oven?" }, { "from": "gpt", "value": "No, the clock is not to the left of the oven." }, { "from": "human", "value": "Is the clock below the oven?" }, { "from": "gpt", "value": "No, the clock is not below the oven." } ], "question": "Is the clock below the oven?", "question_id": "sealvqa_spatial_74", "search": 1, "target_instances": [ { "bbox": [ 292.44, 180.76, 40.2, 43.75 ], "instance_id": "", "name": "clock" }, { "bbox": [ 145.43, 274.54, 59.88, 84.84 ], "instance_id": "", "name": "oven" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the clock below the oven?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the sink is below the clock." }
{ "answer": "Yes, the sink is below the clock.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000104326.jpg", "index": "sealvqa_spatial_75", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the clock to the left of the sink?" }, { "from": "gpt", "value": "No, the clock is not to the left of the sink." }, { "from": "human", "value": "Is the sink below the clock?" }, { "from": "gpt", "value": "Yes, the sink is below the clock." } ], "question": "Is the sink below the clock?", "question_id": "sealvqa_spatial_75", "search": 1, "target_instances": [ { "bbox": [ 292.44, 180.76, 40.2, 43.75 ], "instance_id": "", "name": "clock" }, { "bbox": [ 242.97, 294.4, 42.3, 13.06 ], "instance_id": "", "name": "sink" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the sink below the clock?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The bowl is on the left side of the sandwich." }
{ "answer": "The bowl is on the left side of the sandwich.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000008922.jpg", "index": "sealvqa_spatial_76", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the bowl on the left or right side of the sandwich?" }, { "from": "gpt", "value": "The bowl is on the left side of the sandwich." } ], "question": "Is the bowl on the left or right side of the sandwich?", "question_id": "sealvqa_spatial_76", "search": 1, "target_instances": [ { "bbox": [ 321.06, 340.52, 54.72, 13.88 ], "instance_id": "", "name": "bowl" }, { "bbox": [ 402.53, 340.13, 26.18, 8.6 ], "instance_id": "", "name": "sandwich" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the bowl on the left or right side of the sandwich?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The bowl is on the right side of the sink." }
{ "answer": "The bowl is on the right side of the sink.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000413435.jpg", "index": "sealvqa_spatial_77", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the bowl on the left or right side of the sink?" }, { "from": "gpt", "value": "The bowl is on the right side of the sink." } ], "question": "Is the bowl on the left or right side of the sink?", "question_id": "sealvqa_spatial_77", "search": 1, "target_instances": [ { "bbox": [ 449.86, 348.91, 21.5, 12.79 ], "instance_id": "", "name": "bowl" }, { "bbox": [ 288.15, 357.87, 143.59, 57.44 ], "instance_id": "", "name": "sink" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the bowl on the left or right side of the sink?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The cup is above the sink." }
{ "answer": "The cup is above the sink.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000413435.jpg", "index": "sealvqa_spatial_78", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the sink to the left of the cup?" }, { "from": "gpt", "value": "Yes, the sink is to the left of the cup." }, { "from": "human", "value": "Is the cup above or below the sink?" }, { "from": "gpt", "value": "The cup is above the sink." } ], "question": "Is the cup above or below the sink?", "question_id": "sealvqa_spatial_78", "search": 1, "target_instances": [ { "bbox": [ 456.17, 329.76, 25.92, 25.06 ], "instance_id": "", "name": "cup" }, { "bbox": [ 288.15, 357.87, 143.59, 57.44 ], "instance_id": "", "name": "sink" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the cup above or below the sink?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The microwave is above the bottle." }
{ "answer": "The microwave is above the bottle.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000530384.jpg", "index": "sealvqa_spatial_79", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the microwave to the left of the bottle?" }, { "from": "gpt", "value": "Yes, the microwave is to the left of the bottle." }, { "from": "human", "value": "Is the microwave above or below the bottle?" }, { "from": "gpt", "value": "The microwave is above the bottle." } ], "question": "Is the microwave above or below the bottle?", "question_id": "sealvqa_spatial_79", "search": 1, "target_instances": [ { "bbox": [ 465.08, 234.42, 13.48, 35.01 ], "instance_id": "", "name": "bottle" }, { "bbox": [ 213.99, 149.92, 50.52, 46.74 ], "instance_id": "", "name": "microwave" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the microwave above or below the bottle?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the bottle is not above the toaster." }
{ "answer": "No, the bottle is not above the toaster.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000530384.jpg", "index": "sealvqa_spatial_80", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the bottle on the left or right side of the toaster?" }, { "from": "gpt", "value": "The bottle is on the right side of the toaster." }, { "from": "human", "value": "Is the bottle above the toaster?" }, { "from": "gpt", "value": "No, the bottle is not above the toaster." } ], "question": "Is the bottle above the toaster?", "question_id": "sealvqa_spatial_80", "search": 1, "target_instances": [ { "bbox": [ 465.08, 234.42, 13.48, 35.01 ], "instance_id": "", "name": "bottle" }, { "bbox": [ 240.97, 213.87, 21.76, 18.97 ], "instance_id": "", "name": "toaster" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the bottle above the toaster?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The truck is to the left of the cup." }
{ "answer": "The truck is to the left of the cup.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000321522.jpg", "index": "sealvqa_spatial_81", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the truck to the left or right of the cup?" }, { "from": "gpt", "value": "The truck is to the left of the cup." } ], "question": "Is the truck to the left or right of the cup?", "question_id": "sealvqa_spatial_81", "search": 1, "target_instances": [ { "bbox": [ 367.56, 108.95, 47.16, 36.06 ], "instance_id": "", "name": "cup" }, { "bbox": [ 44.78, 106.9, 81.28, 42.77 ], "instance_id": "", "name": "truck" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the truck to the left or right of the cup?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the cup is not on the left side of the car." }
{ "answer": "No, the cup is not on the left side of the car.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000321522.jpg", "index": "sealvqa_spatial_82", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the cup on the left side of the car?" }, { "from": "gpt", "value": "No, the cup is not on the left side of the car." } ], "question": "Is the cup on the left side of the car?", "question_id": "sealvqa_spatial_82", "search": 1, "target_instances": [ { "bbox": [ 67.26, 108.63, 49.38, 41.85 ], "instance_id": "", "name": "car" }, { "bbox": [ 367.56, 108.95, 47.16, 36.06 ], "instance_id": "", "name": "cup" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the cup on the left side of the car?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the cell phone is not below the backpack." }
{ "answer": "No, the cell phone is not below the backpack.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000069969.jpg", "index": "sealvqa_spatial_83", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the backpack to the right of the cell phone?" }, { "from": "gpt", "value": "No, the backpack is not to the right of the cell phone." }, { "from": "human", "value": "Is the cell phone below the backpack?" }, { "from": "gpt", "value": "No, the cell phone is not below the backpack." } ], "question": "Is the cell phone below the backpack?", "question_id": "sealvqa_spatial_83", "search": 1, "target_instances": [ { "bbox": [ 530.9, 258.6, 18.67, 20.14 ], "instance_id": "", "name": "cell phone" }, { "bbox": [ 381.23, 287.28, 46.29, 38 ], "instance_id": "", "name": "backpack" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the cell phone below the backpack?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the dining table is not to the left of the sink." }
{ "answer": "No, the dining table is not to the left of the sink.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000199634.jpg", "index": "sealvqa_spatial_84", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the dining table to the left of the sink?" }, { "from": "gpt", "value": "No, the dining table is not to the left of the sink." } ], "question": "Is the dining table to the left of the sink?", "question_id": "sealvqa_spatial_84", "search": 1, "target_instances": [ { "bbox": [ 296.1, 254.26, 63.55, 9.19 ], "instance_id": "", "name": "sink" }, { "bbox": [ 408.47, 259.89, 165.48, 51.04 ], "instance_id": "", "name": "dining table" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the dining table to the left of the sink?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the microwave is not on the right side of the dining table." }
{ "answer": "No, the microwave is not on the right side of the dining table.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000199634.jpg", "index": "sealvqa_spatial_85", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the microwave on the right side of the dining table?" }, { "from": "gpt", "value": "No, the microwave is not on the right side of the dining table." } ], "question": "Is the microwave on the right side of the dining table?", "question_id": "sealvqa_spatial_85", "search": 1, "target_instances": [ { "bbox": [ 203.59, 232.96, 50.47, 27.7 ], "instance_id": "", "name": "microwave" }, { "bbox": [ 408.47, 259.89, 165.48, 51.04 ], "instance_id": "", "name": "dining table" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the microwave on the right side of the dining table?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the sink is not to the left of the microwave." }
{ "answer": "No, the sink is not to the left of the microwave.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000199634.jpg", "index": "sealvqa_spatial_86", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the sink to the left of the microwave?" }, { "from": "gpt", "value": "No, the sink is not to the left of the microwave." } ], "question": "Is the sink to the left of the microwave?", "question_id": "sealvqa_spatial_86", "search": 1, "target_instances": [ { "bbox": [ 203.59, 232.96, 50.47, 27.7 ], "instance_id": "", "name": "microwave" }, { "bbox": [ 296.1, 254.26, 63.55, 9.19 ], "instance_id": "", "name": "sink" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the sink to the left of the microwave?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The sink is below the potted plant." }
{ "answer": "The sink is below the potted plant.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000170365.jpg", "index": "sealvqa_spatial_87", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the potted plant to the right of the sink?" }, { "from": "gpt", "value": "Yes, the potted plant is to the right of the sink." }, { "from": "human", "value": "Is the sink above or below the potted plant?" }, { "from": "gpt", "value": "The sink is below the potted plant." } ], "question": "Is the sink above or below the potted plant?", "question_id": "sealvqa_spatial_87", "search": 1, "target_instances": [ { "bbox": [ 243.73, 190.97, 63.85, 89.8 ], "instance_id": "", "name": "potted plant" }, { "bbox": [ 98.73, 331.85, 122.91, 64.91 ], "instance_id": "", "name": "sink" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the sink above or below the potted plant?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the sink is below the bowl." }
{ "answer": "Yes, the sink is below the bowl.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000283190.jpg", "index": "sealvqa_spatial_88", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the bowl to the left of the sink?" }, { "from": "gpt", "value": "No, the bowl is not to the left of the sink." }, { "from": "human", "value": "Is the sink below the bowl?" }, { "from": "gpt", "value": "Yes, the sink is below the bowl." } ], "question": "Is the sink below the bowl?", "question_id": "sealvqa_spatial_88", "search": 1, "target_instances": [ { "bbox": [ 95, 211.1, 137.21, 24.95 ], "instance_id": "", "name": "sink" }, { "bbox": [ 318.66, 194.44, 34.02, 14.63 ], "instance_id": "", "name": "bowl" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the sink below the bowl?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The book is above the vase." }
{ "answer": "The book is above the vase.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000523978.jpg", "index": "sealvqa_spatial_89", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the vase to the left of the book?" }, { "from": "gpt", "value": "No, the vase is not to the left of the book." }, { "from": "human", "value": "Is the book above or below the vase?" }, { "from": "gpt", "value": "The book is above the vase." } ], "question": "Is the book above or below the vase?", "question_id": "sealvqa_spatial_89", "search": 1, "target_instances": [ { "bbox": [ 122.43, 83.92, 4.79, 19.04 ], "instance_id": "", "name": "book" }, { "bbox": [ 174.47, 118.6, 14.34, 29.79 ], "instance_id": "", "name": "vase" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the book above or below the vase?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The sink is below the bowl." }
{ "answer": "The sink is below the bowl.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000315740.jpg", "index": "sealvqa_spatial_90", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the sink on the left side of the bowl?" }, { "from": "gpt", "value": "Yes, the sink is on the left side of the bowl." }, { "from": "human", "value": "Is the sink above or below the bowl?" }, { "from": "gpt", "value": "The sink is below the bowl." } ], "question": "Is the sink above or below the bowl?", "question_id": "sealvqa_spatial_90", "search": 1, "target_instances": [ { "bbox": [ 467.65, 218.64, 27.7, 17.28 ], "instance_id": "", "name": "bowl" }, { "bbox": [ 218.5, 272.74, 105.12, 38.53 ], "instance_id": "", "name": "sink" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the sink above or below the bowl?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The sink is below the microwave." }
{ "answer": "The sink is below the microwave.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000315740.jpg", "index": "sealvqa_spatial_91", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the microwave to the left of the sink?" }, { "from": "gpt", "value": "No, the microwave is not to the left of the sink." }, { "from": "human", "value": "Is the sink above or below the microwave?" }, { "from": "gpt", "value": "The sink is below the microwave." } ], "question": "Is the sink above or below the microwave?", "question_id": "sealvqa_spatial_91", "search": 1, "target_instances": [ { "bbox": [ 526.11, 118.93, 112.3, 71.9 ], "instance_id": "", "name": "microwave" }, { "bbox": [ 218.5, 272.74, 105.12, 38.53 ], "instance_id": "", "name": "sink" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the sink above or below the microwave?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the bowl is on the right side of the potted plant." }
{ "answer": "Yes, the bowl is on the right side of the potted plant.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000302038.jpg", "index": "sealvqa_spatial_92", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the bowl on the right side of the potted plant?" }, { "from": "gpt", "value": "Yes, the bowl is on the right side of the potted plant." } ], "question": "Is the bowl on the right side of the potted plant?", "question_id": "sealvqa_spatial_92", "search": 1, "target_instances": [ { "bbox": [ 373.51, 136.83, 65.47, 130.26 ], "instance_id": "", "name": "potted plant" }, { "bbox": [ 505.91, 265.93, 39.74, 10.66 ], "instance_id": "", "name": "bowl" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the bowl on the right side of the potted plant?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the cup is on the right side of the potted plant." }
{ "answer": "Yes, the cup is on the right side of the potted plant.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000302038.jpg", "index": "sealvqa_spatial_93", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the cup on the right side of the potted plant?" }, { "from": "gpt", "value": "Yes, the cup is on the right side of the potted plant." } ], "question": "Is the cup on the right side of the potted plant?", "question_id": "sealvqa_spatial_93", "search": 1, "target_instances": [ { "bbox": [ 373.51, 136.83, 65.47, 130.26 ], "instance_id": "", "name": "potted plant" }, { "bbox": [ 444.89, 264.24, 12.02, 21.68 ], "instance_id": "", "name": "cup" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the cup on the right side of the potted plant?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the bowl is not on the left side of the cup." }
{ "answer": "No, the bowl is not on the left side of the cup.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 2, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000302038.jpg", "index": "sealvqa_spatial_94", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the bowl on the left side of the cup?" }, { "from": "gpt", "value": "No, the bowl is not on the left side of the cup." } ], "question": "Is the bowl on the left side of the cup?", "question_id": "sealvqa_spatial_94", "search": 1, "target_instances": [ { "bbox": [ 444.89, 264.24, 12.02, 21.68 ], "instance_id": "", "name": "cup" }, { "bbox": [ 505.91, 265.93, 39.74, 10.66 ], "instance_id": "", "name": "bowl" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the bowl on the left side of the cup?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "The tie is above the dining table." }
{ "answer": "The tie is above the dining table.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000243600.jpg", "index": "sealvqa_spatial_95", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the dining table to the right of the tie?" }, { "from": "gpt", "value": "Yes, the dining table is to the right of the tie." }, { "from": "human", "value": "Is the tie above or below the dining table?" }, { "from": "gpt", "value": "The tie is above the dining table." } ], "question": "Is the tie above or below the dining table?", "question_id": "sealvqa_spatial_95", "search": 1, "target_instances": [ { "bbox": [ 129.89, 185.53, 92.84, 106.48 ], "instance_id": "", "name": "dining table" }, { "bbox": [ 93.12, 171.52, 6.98, 10.57 ], "instance_id": "", "name": "tie" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the tie above or below the dining table?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the vase is not below the dining table." }
{ "answer": "No, the vase is not below the dining table.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000243600.jpg", "index": "sealvqa_spatial_96", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the dining table to the right of the vase?" }, { "from": "gpt", "value": "No, the dining table is not to the right of the vase." }, { "from": "human", "value": "Is the vase below the dining table?" }, { "from": "gpt", "value": "No, the vase is not below the dining table." } ], "question": "Is the vase below the dining table?", "question_id": "sealvqa_spatial_96", "search": 1, "target_instances": [ { "bbox": [ 129.89, 185.53, 92.84, 106.48 ], "instance_id": "", "name": "dining table" }, { "bbox": [ 430.68, 87.98, 21.43, 27.35 ], "instance_id": "", "name": "vase" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the vase below the dining table?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the tie is below the potted plant." }
{ "answer": "Yes, the tie is below the potted plant.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000243600.jpg", "index": "sealvqa_spatial_97", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the tie on the left side of the potted plant?" }, { "from": "gpt", "value": "Yes, the tie is on the left side of the potted plant." }, { "from": "human", "value": "Is the tie below the potted plant?" }, { "from": "gpt", "value": "Yes, the tie is below the potted plant." } ], "question": "Is the tie below the potted plant?", "question_id": "sealvqa_spatial_97", "search": 1, "target_instances": [ { "bbox": [ 414.44, 46.63, 51.26, 68.14 ], "instance_id": "", "name": "potted plant" }, { "bbox": [ 93.12, 171.52, 6.98, 10.57 ], "instance_id": "", "name": "tie" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the tie below the potted plant?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "Yes, the clock is above the dining table." }
{ "answer": "Yes, the clock is above the dining table.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000476925.jpg", "index": "sealvqa_spatial_98", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the clock to the left of the dining table?" }, { "from": "gpt", "value": "No, the clock is not to the left of the dining table." }, { "from": "human", "value": "Is the clock above the dining table?" }, { "from": "gpt", "value": "Yes, the clock is above the dining table." } ], "question": "Is the clock above the dining table?", "question_id": "sealvqa_spatial_98", "search": 1, "target_instances": [ { "bbox": [ 387.24, 75.91, 24.48, 26.01 ], "instance_id": "", "name": "clock" }, { "bbox": [ 74.87, 169.68, 83.27, 55.91 ], "instance_id": "", "name": "dining table" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the clock above the dining table?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
sealvqa_spatial
{ "ground_truth": "No, the sink is not below the toilet." }
{ "answer": "No, the sink is not below the toilet.", "bbox_format": "absolute_xywh", "bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format", "conversation_turns": 4, "data_split": "train", "dataset_type": "spatial_relation", "has_targets": true, "image_path": "coco2017/train2017/000000515904.jpg", "index": "sealvqa_spatial_99", "original_conversations": [ { "from": "human", "value": "<image>\nAdditional visual information to focus on: <object>; <object>.\nIs the sink to the left or right of the toilet?" }, { "from": "gpt", "value": "The sink is to the left of the toilet." }, { "from": "human", "value": "Is the sink below the toilet?" }, { "from": "gpt", "value": "No, the sink is not below the toilet." } ], "question": "Is the sink below the toilet?", "question_id": "sealvqa_spatial_99", "search": 1, "target_instances": [ { "bbox": [ 104.85, 289.91, 68.24, 47.3 ], "instance_id": "", "name": "toilet" }, { "bbox": [ 0.63, 208.91, 74.35, 45.07 ], "instance_id": "", "name": "sink" } ] }
[ { "content": "", "role": "system" }, { "content": "<image>\nIs the sink below the toilet?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ", "role": "user" } ]
sealvqa_spatial_spatial
visual_toolbox_v2
End of preview. Expand in Data Studio

SEAL VQA Spatial Relation Dataset

This dataset contains spatial relation questions from SEAL VQA.

Dataset Information

  • Total samples: 26,961
  • COCO 2017 only: True
  • Random seed: 42
  • Image format: Image paths only (no image data embedded)

Abilities

  • sealvqa_spatial_spatial: 26,961 samples

Bounding Box Format

Format: absolute_xywh

All bounding boxes use absolute pixel coordinates with the format:

[x, y, width, height]

Usage Example

import json
from PIL import Image, ImageDraw

# Load dataset
with open('spatial_data.json', 'r') as f:
    dataset = json.load(f)

sample = dataset[0]
image_path = sample['images'][0]
question = sample['extra_info']['question']
answer = sample['extra_info']['answer']

print(f"Q: {question}")
print(f"A: {answer}")

# Draw bounding boxes
image = Image.open(image_path)
draw = ImageDraw.Draw(image)
for instance in sample['extra_info']['target_instances']:
    x, y, w, h = instance['bbox']
    draw.rectangle([x, y, x + w, y + h], outline='red', width=2)
    draw.text((x, y-15), instance['name'], fill='red')

Generation Command

python build_spatial_dataset.py \
    --num_samples 999999 \
    --seed 42 \
    --coco_only
Downloads last month
46