VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding

@misc{zhang2025videoitgmultimodalvideo,
      title={VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding},
      author={Lei Zhang and Jose M. Alvarez and Zhiqi Li and Guo Chen and Zhiding Yu and Shihao Wang and Minghan Li and Guilin Li and De-an Huang},
      year={2025},
      eprint={2507.13353},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2507.13353},
}