本模型卡片旨在提供“MVBench: A Comprehensive Multi-modal Video Understanding Benchmark”的模型信息。
如果您认为本工作对您的研究有帮助，请考虑引用 VideoChat2。您的认可将极大帮助我们持续向研究社区贡献资源。
@article{li2023videochat,
title={VideoChat: Chat-Centric Video Understanding},
author={KunChang Li, Yinan He, Yi Wang, Yizhuo Li, Wenhai Wang, Ping Luo, Yali Wang, Limin Wang, and Yu Qiao},
journal={arXiv preprint arXiv:2305.06355},
year={2023}
}
@misc{li2023mvbench,
title={MVBench: A Comprehensive Multi-modal Video Understanding Benchmark},
author={Kunchang Li and Yali Wang and Yinan He and Yizhuo Li and Yi Wang and Yi Liu and Zun Wang and Jilan Xu and Guo Chen and Ping Luo and Limin Wang and Yu Qiao},
year={2023},
eprint={2311.17005},
archivePrefix={arXiv},
primaryClass={cs.CV}
}