@article{videotokenmergingforlongformvideo,
  title = {Video Token Merging for Long-form Video Understanding},
  author = {Seon-Ho Lee and Jue Wang and Zhikang Zhang and David Fan and Xinyu Li},
  year = {2024},
  eprint = {2410.23782},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.23782v1},
}