← Back to literature explorer
Unsupervised & Semi-Supervised From survey PDF — verify links

VLAVAD

VLAVAD — Semantic Normality Modeling

BMVC · 2024

Survey summary

VLAVAD pairs a cross-modal pretrained model with a Selective-Prompt Adapter that selects relevant semantic space, and a Sequence State Space Module that detects temporal inconsistencies in mapped low-dimensional semantic features, enhancing interpretability of unsupervised anomaly detection.

Unsupervised & Semi-Supervised

Unsupervised & Semi-SupervisedSemantic Normality Modeling
Unsupervised & Semi-SupervisedVLM promptsSelective Prompt AdapterSequence modeling