Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective 事件

Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective arXiv:2605.26441v1 Announce Type: new Abstract: This paper addresses the challenging task of weakly-supervised video temporal grounding. Existing approaches are generally based on the moment proposal selection framework that utilizes contrastive learning and reconstruction paradigm for scoring the pre-defined moment proposals. Although they have achieved significant progress, we argue that their current frameworks hav