cs.CVNov 6, 2026

Multimodal Training with Knowledge Traction for Video Anomaly Detection

Authors: Xiao Tan

Organizations: Xidian University, Xi’an, China

Abstract

The task of weakly supervised video anomaly detection is challenging. Existing approaches mainly model video frame features and determine whether anomalies are present based on their magnitudes. In this work, we propose a novel method that incorporates external knowledge into training to improve model performance, robustness, and generalization. We leverage textual prompts and a large language model (LLM) to establish prior information for the specific task, and employ dictionary learning to normalize and compress this information. Moreover, during experiments, we observed inconsistencies in the textual descriptions extracted from similar video frames by image caption models. To address this, we devise a method that leverages an LLM and auxiliary information to ensure consistency in the textual descriptions of similar frames within a video. Finally, we introduce a feature processing approach that incorporates prior knowledge and cross-modal attention mechanisms. This approach learns the relationships and characteristics among different modalities to construct more accurate and reliable feature representations, thereby improving the accuracy and stability of downstream tasks. Experimental results demonstrate that our method surpasses other state-of-the-art approaches.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Decoupled Sensitivity-Consistency Learning for Weakly Supervised Video Anomaly Detection

    Mar 20, 2026Hantao Zheng, Ning Han, Yawen Zeng +1Video Anomaly DetectionWeakly Supervised Video Anomaly Detection

  2. MuST-VAD: Mutual Structured Learning for Video Anomaly Detection

    Aug 7, 2026Satoshi Hashimoto, Hitoshi Nishimura, Mori KurokawaVLM AdaptationWeakly Supervised Video Anomaly Detection

  3. Structured Evidence Selection for Weakly Supervised Video Anomaly Detection

    Jul 11, 2026Chenglizhao Chen, Tianxiang Nan, Wen Li +4Anomaly LocalizationWeakly Supervised Video Anomaly Detection