SVTA is a large synthetic video-text benchmark with 41,315 videos covering 68 anomaly types, created by LLM-generated captions and text-to-video generation, and evaluated with three retrieval baselines.
Context recov- ery and knowledge retrieval: A novel two-stream framework for video anomaly detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Scalable Video Anomaly Retrieval: A Synthetic Video-Text Benchmark
SVTA is a large synthetic video-text benchmark with 41,315 videos covering 68 anomaly types, created by LLM-generated captions and text-to-video generation, and evaluated with three retrieval baselines.