@article{testatemporalspatialtokenaggregationfor, title = {TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding}, author = {Shuhuai Ren and Sishuo Chen and Shicheng Li and Xu sun and Lu Hou}, year = {2023}, eprint = {2310.19060}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2310.19060v1}, }