Yuying Ge, Yizhuo Li 0001, Yixiao Ge, Ying Shan. Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2025, Nashville, TN, USA, June 11-15, 2025. pages 13606-13617, Computer Vision Foundation / IEEE, 2025. [doi]
Abstract is missing.