@inproceedings{wang2025videoitg,
  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 Liu and Jan Kautz and Jose M. Alvarez and Lei Zhang and Zhiding Yu},
  year = {2026},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2507.13353},
  archiveprefix = {arxiv},
}