Aug 2026
DiaVTG: multi-turn reasoning framework for video temporal grounding
DiaVTG, a novel VTG framework designed to enhance temporal localization precision, is proposed to reformulate temporal localization as a video understanding problem and demonstrates that the training-free method consistently improves performance across various Vid-LLM architectures.
Hong-Yu Huang, Junyi Yang, Sipeng Yang et al.
· The Visual Computer · 0 citations