@misc{shangguan2024tomato,
  title={TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models},
  author={Ziyao Shangguan and Chuhan Li and Yuxuan Ding and Yanan Zheng and Yilun Zhao and Tesca Fitzgerald and Arman Cohan},
  year={2024},
  eprint={2410.23266},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2410.23266}
}