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.
Gramian multimodal representation learning and alignment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 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.