A new benchmark, a training-free framework, and a joint metric for video anomaly detection that combines temporal grounding with semantic understanding.
Improved anomaly detection in surveillance videos with multiple probabilistic models inference,
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.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
VAGU & GtS: LLM-Based Benchmark and Framework for Joint Video Anomaly Grounding and Understanding
A new benchmark, a training-free framework, and a joint metric for video anomaly detection that combines temporal grounding with semantic understanding.