@article{videoxumcrossmodalvisualandtextural,
  title = {VideoXum: Cross-modal Visual and Textural Summarization of Videos},
  author = {Jingyang Lin and Hang Hua and Ming Chen and Yikang Li and Jenhao Hsiao and Chiuman Ho and Jiebo Luo},
  year = {2023},
  eprint = {2303.12060},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2303.12060v3},
}