TaRO improves video temporal grounding in MLLMs via constructive reasoning exploration from dense captions and a temporal-sensitivity reward that uses logit drops on disrupted event boundaries, followed by curriculum learning to SOTA results.
arXiv preprint arXiv:2301.00514 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3verdicts
UNVERDICTED 3representative citing papers
Models frames and words as cooperative game players to value uncertain vision-language correspondences for proposal-free moment localization, reporting superior results on Charades-STA and ActivityNet Caption.
A multi-scale and cross-scale contrastive learning framework uses intra-encoder stage features and a new sampling process to link short-range and long-range video moments for temporal grounding.
citing papers explorer
-
Temporal-Aware Reasoning Optimization for Video Temporal Grounding
TaRO improves video temporal grounding in MLLMs via constructive reasoning exploration from dense captions and a temporal-sensitivity reward that uses logit drops on disrupted event boundaries, followed by curriculum learning to SOTA results.
-
Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective
Models frames and words as cooperative game players to value uncertain vision-language correspondences for proposal-free moment localization, reporting superior results on Charades-STA and ActivityNet Caption.
-
Multi-Scale Contrastive Learning for Video Temporal Grounding
A multi-scale and cross-scale contrastive learning framework uses intra-encoder stage features and a new sampling process to link short-range and long-range video moments for temporal grounding.