A training-free glance-then-scrutinize pipeline and a reinforcement-learned tool-calling agent both improve joint temporal grounding and semantic understanding of video anomalies on a new benchmark.
In: European Conference on Computer Vision, pp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Glance, Scrutinize, and Think: Advancing Video Anomaly Detection from Training-Free to Agentic Reasoning
A training-free glance-then-scrutinize pipeline and a reinforcement-learned tool-calling agent both improve joint temporal grounding and semantic understanding of video anomalies on a new benchmark.