作者位次 #5/13CVPR 2026Poster· Computer Vision & Pattern Recognition
Hear What You See: Video-to-Audio Generation with Diffusion Transformer and Semantic-Temporal Alignment-Ranked Direct Preference Optimization
Kai Wang · Tao Zhou · jiayi lei · Tmall Group of Alibaba) · Jinman Zhao · Weiguo Pian · Yuan Cheng · Yapeng Tian · Peng Gao · Bin Fu · Yihao Liu · Dimitrios Hatzinakos · Yuewen Cao