Tianyu Fu 0004, Tengxuan Liu, Qinghao Han, Guohao Dai 0001, Shengen Yan, Huazhong Yang, Xuefei Ning, Yu Wang 0002. FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Vision Language Models. In IEEE/CVF International Conference on Computer Vision, ICCV 2025, Honolulu, HI, USA, October 19-25, 2025. pages 22654-22663, IEEE, 2025. [doi]
Abstract is missing.