@article{cfsumatransformerbasedmultimodalvideo,
  title = {CFSum: A Transformer-Based Multi-Modal Video Summarization Framework With Coarse-Fine Fusion},
  author = {Yaowei Guo and Jiazheng Xing and Xiaojun Hou and Shuo Xin and Juntao Jiang and Demetri Terzopoulos and Chenfanfu Jiang and Yong liu},
  year = {2025},
  eprint = {2503.00364},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.00364v1},
}