Ruyang Liu, Shangkun Sun, Haoran Tang, Wei Gao 0003, Ge Li 0002. Flow4Agent: Long-form Video Understanding via Motion Prior from Optical Flow. In IEEE/CVF International Conference on Computer Vision, ICCV 2025, Honolulu, HI, USA, October 19-25, 2025. pages 23817-23827, IEEE, 2025. [doi]
Abstract is missing.