← Back to literature explorer
Training-Free From survey PDF — verify links

SUVAD

SUVAD — Semantic Understanding

ICASSP · 2025

Survey summary

SUVAD is a training-free MLLM-based method that generates detailed textual descriptions of video content for semantic understanding, then detects anomalies directly via an LLM from those descriptions, with techniques to mitigate MLLM hallucination and support flexible, scene-adaptable anomaly definitions.

Training-Free

Training-FreeSemantic Understanding
Training-FreeMLLMEvent listsFlexible definitions