VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection

@misc{huang2024videoespressolargescalechainofthought,
      title={VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection}, 
      author={Wei Huang and Si Liu and Xiaojuan Qi and Le Zhuo and Xu Zhou and Yue Liao and Xiu Su and Shifeng Zhang and Songhao Han and Hairong Shi},
      year={2024},
      eprint={2411.14794},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2411.14794}, 
}