ICCV 2025 poster

DynImg: Key Frames with Visual Prompts are Good Representation for Multi-Modal Video Understanding

1citations

1

Citations

#691

in ICCV 2025

of 2701 papers

7

Authors

1

Data Points

Authors

Xiaoyi Bao Chen-Wei Xie Hao Tang Tingyu Weng Xiaofeng Wang Yun Zheng Xingang Wang

Citation History

Jan 26, 2026

1