@article{efficientvideotransformerswithspatial, title = {Efficient Video Transformers with Spatial-Temporal Token Selection}, author = {Junke Wang and Xitong Yang and Hengduo Li and Li Liu and Zuxuan Wu and Yu-Gang Jiang}, year = {2021}, eprint = {2111.11591}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2111.11591v2}, }