MS-DETR: Towards Effective Video Moment Retrieval and Highlight Detection by Joint Motion-Semantic Learning

Hongxu Ma, Guanshuo Wang, Fufu Yu, Qiong Jia, Shouhong Ding

BibTeX
@inproceedings{ma2025ms,
  author = {Hongxu Ma and Guanshuo Wang and Fufu Yu and Qiong Jia and Shouhong Ding},
  title = {{MS-DETR: Towards Effective Video Moment Retrieval and Highlight Detection by Joint Motion-Semantic Learning}},
  booktitle = {ACM Multimedia},
  year = {2025},
  url = {https://openreview.net/forum?id=l7P1BsAGbp},
}
Figure