arxiv:2510.05034
HangHua
hhua2
·
AI & ML interests
None yet
Recent Activity
authored
a paper
5 days ago
Caption Anything in Video: Fine-grained Object-centric Captioning via
Spatiotemporal Multimodal Prompting
authored
a paper
5 days ago
The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report
authored
a paper
5 days ago
MMIG-Bench: Towards Comprehensive and Explainable Evaluation of
Multi-Modal Image Generation Models
Organizations
