Jul 2026
ScanFocus: A Coarse-to-Fine Framework for Spatio-Temporal Video Grounding
A novel coarse-to-fine framework that decouples the STVG task into a global spatio-temporal scan and a local boundary focus and introduces the Semantic-Guided Temporal Aggregator (SGTA) in the refinement stage, which explicitly models short-term temporal interactions under semantic guidance.
Kai Chen, Ming Dai, Wenxuan Cheng et al.
· arXiv.org · 0 citations