@article{chatvideoatrackletcentricmultimodaland,
  title = {ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding System},
  author = {Junke Wang and Dongdong Chen and Chong Luo and Xiyang Dai and Lu Yuan and Zuxuan Wu and Yu-Gang Jiang},
  year = {2023},
  eprint = {2304.14407},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2304.14407v2},
}