F2G improves video temporal grounding accuracy by decoupling event identification from boundary measurement using predictive temporal perception to create citable evidence segments for LLM reasoning.
and Rubinstein, Michael and Irani, Michal and Dekel, Tali , booktitle=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Foresee-to-Ground: From Predictive Temporal Perception to Evidence-Driven Reasoning for Video Temporal Grounding
F2G improves video temporal grounding accuracy by decoupling event identification from boundary measurement using predictive temporal perception to create citable evidence segments for LLM reasoning.