VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding

@misc{wangThu Jul 17 2025 17:59:59 GMT+0000 (Coordinated Universal Time)videoitgmultimodalvideo,
      title={VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding},
      author={Shihao Wang and Guo Chen and De-an Huang and Zhiqi Li and Minghan Li and Guilin Li and Jose M. Alvarez and Lei Zhang and Zhiding Yu},
      year={Thu Jul 17 2025 17:59:59 GMT+0000 (Coordinated Universal Time)},
      eprint={2507.13353/sso-callback},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2507.13353/sso-callback},
}