AI & ML interests
Computer Vision; Video Understanding; Action Recognition
Recent Activity
Papers
SAM 2++: Tracking Anything at Any Granularity
Joint Modeling of Feature, Correspondence, and a Compressed Memory for Video Object Segmentation
Organization Card
We release the code, model and data of the research work done by the Multimedia Computing Group (MCG), Nanjing University🔥
models
37
MCG-NJU/SAM2-Plus
Updated
MCG-NJU/MotionRAG
Image-to-Video
•
Updated
•
5
MCG-NJU/StreamForest-Pretrain-Qwen2-7B
8B
•
Updated
•
4
•
1
MCG-NJU/StreamForest-Drive-Qwen2-7B
8B
•
Updated
•
14
•
1
MCG-NJU/StreamForest-Qwen2-7B
8B
•
Updated
•
123
•
1
MCG-NJU/KS-Gen
Updated
•
2
MCG-NJU/PixNerd-XXL-P16-T2I
Text-to-Image
•
Updated
•
11
MCG-NJU/PixNerd-XL-P16-C2I
Unconditional Image Generation
•
Updated
•
5
MCG-NJU/DMM
Text-to-Image
•
Updated
•
22
•
16
MCG-NJU/DDT-XL-22en6de-R256
Text-to-Image
•
Updated
•
4
datasets
11
MCG-NJU/Tracking-Any-Granularity
Updated
•
76
MCG-NJU/ODV-Bench
Viewer
•
Updated
•
7.9k
•
101
MCG-NJU/StreamForest-Annodata
Updated
•
244
•
1
MCG-NJU/CaReBench
Viewer
•
Updated
•
1k
•
161
MCG-NJU/OVBench
Viewer
•
Updated
•
1.46k
•
907
•
4
MCG-NJU/KS-Gen
Viewer
•
Updated
•
24k
•
42
•
1
MCG-NJU/VideoChatOnline-IT
Viewer
•
Updated
•
221k
•
121
•
4
MCG-NJU/SportsShot
Viewer
•
Updated
•
1.2k
•
21
MCG-NJU/SportsMOT
Viewer
•
Updated
•
240
•
105
•
5
MCG-NJU/SportsHHI
Preview
•
Updated
•
36
•
4