CFSum: A Transformer-Based Multi-Modal Video Summarization Framework With Coarse-Fine Fusion.

Yaowei Guo, Jiazheng Xing, Xiaojun Hou, Shuo Xin, Juntao Jiang, Demetri Terzopoulos, Chenfanfu Jiang, Yong Liu

Browse the full ICASSP paper archive.