← Back to literature explorer
Weakly Supervised From survey PDF — verify links

TEVAD

TEVAD — Caption-Guided Semantics

CVPR · 2023

Survey summary

TEVAD (Text-Empowered VAD) generates dense captions for video snippets and fuses text and visual features for anomaly detection, improving accuracy and robustness on ShanghaiTech, UCF-Crime, XD-Violence, and UCSD-Pedestrians while using word-level caption contributions to explain predictions.

Weakly Supervised

Weakly SupervisedCaption-Guided Semantics
Weakly SupervisedDense captionsSentence embeddingsInterpretability