SRTube: Video-Language Pre-Training with Action-Centric Video Tube Features and Semantic Role Labeling

Ju-Hee Lee, Je-Won KangCVPR 2024 · DOI

BibTeX
@inproceedings{lee2024srtube,
  author = {Ju-Hee Lee and Je-Won Kang},
  title = {{SRTube: Video-Language Pre-Training with Action-Centric Video Tube Features and Semantic Role Labeling}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year = {2024},
  doi = {10.1109/cvpr52733.2024.01299},
}

Loading related content...

Figure