Jie Lei    @jayleicn
Presenting "QVHighlights": 10K YouTube videos dataset annotated w. human written queries, clip-wise relevance, highlightness/saliency scores & Moment-DETR model for joint moment localization + highlight/saliency prediction https://t.co/FnEF93FuCc tlberg @mohitban47 @uncnlp 1/n
More from Jie Lei







 







Jie Lei

Jannik Kossen

Rowan Zellers

Xiaolong Wang

MBZ

Neil Band