@article{vamosversatileactionmodelsforvideo, title = {Vamos: Versatile Action Models for Video Understanding}, author = {Shijie Wang and Qi Zhao and Minh Quan Do and Nakul Agarwal and Kwonjoon Lee and Chen Sun}, year = {2023}, eprint = {2311.13627}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2311.13627v3}, }