Temporal Video Grounding
Overview
Temporal video grounding studies how to identify when a described action, event, or state occurs in a video, often returning one or more time intervals. Methods range from proposal-based models and cross-modal alignment to zero-shot video-language models, query-guided frame selection, and agents that search long videos in stages. Training commonly uses temporal annotations and benchmarks such as QVHighlights, Charades-STA, and ActivityNet-Captions, while newer work explores weak supervision, reinforcement learning, and open-world queries. A central challenge is that fluent answers and broad event recognition do not guarantee precise, faithful evidence localization, especially in long videos or when queries are ambiguous or match multiple moments.
Latest papers
169 papers28 papers in the last four weeks, up 115% on the four weeks before. 0.2% of all new papers.