mlsanityData to 14 Oct 2026

GMFVAD: Using Grained Multi-modal Feature to Improve Video Anomaly Detection

arXiv 2510.20268 ↗First posted 23 Oct 2025cs.CV cs.MMcited by 0

Not on the map. Why?

Abstract (arXiv)

Video anomaly detection (VAD) is a challenging task that detects anomalous frames in continuous surveillance videos. Most previous work utilizes the spatio-temporal correlation of visual features to distinguish whether there are abnormalities in video snippets. Recently, some works attempt to introduce multi-modal information, like text feature, to enhance the results of video anomaly detection. However, these works merely incorporate text features into video snippets in a coarse manner, overlooking the significant amount of redundant information that may exist within the video snippets. Therefore, we propose to leverage the diversity among multi-modal information to further refine the extracted features, reducing the redundancy in visual features, and we propose Grained Multi-modal Feature for Video Anomaly Detection (GMFVAD). Specifically, we generate more grained multi-modal feature based on the video snippet, which summarizes the main content, and text features based on the captions of original video will be introduced to further enhance the visual features of highlighted portions. Experiments show that the proposed GMFVAD achieves state-of-the-art performance on four mainly datasets. Ablation experiments also validate that the improvement of GMFVAD is due to the reduction of redundant information.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 52 references that are in the map. First posted on arXiv 23 Oct 2025.

Builds on

36 of 52 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  5. 2017The Kinetics Human Action Video Datasetcited by 1,909
  6. 2018Real-world Anomaly Detection in Surveillance Videoscited by 577
  7. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 564
  8. 2019VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Researchcited by 414
  9. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  10. 2017Temporal Segment Networks for Action Recognition in Videoscited by 279
  11. 2020Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervisioncited by 238
  12. 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 230
24 more
  1. 2019Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detectioncited by 171
  2. 2021SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioningcited by 162
  3. 2018Latent Space Autoregression for Novelty Detectioncited by 149
  4. 2020Anomaly Detection in Video via Self-Supervised and Multi-Task Learningcited by 148
  5. 2021MIST: Multiple Instance Self-Training Framework for Video Anomaly Detectioncited by 138
  6. 2023VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detectioncited by 123
  7. 2019Anomaly Detection in Video Sequence with Appearance-Motion Correspondencecited by 118
  8. 2020Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigmcited by 115
  9. 2018Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Videocited by 111
  10. 2021UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detectioncited by 93
  11. 2023Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detectioncited by 90
  12. 2022MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detectioncited by 89
  13. 2020A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Videocited by 86
  14. 2022CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detectioncited by 67
  15. 2023Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detectioncited by 64
  16. 2024Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLMcited by 64
  17. 2023Open-Vocabulary Video Anomaly Detectioncited by 57
  18. 2020Localizing Anomalies from Weakly-Labeled Videoscited by 52
  19. 2024Hawk: Learning to Understand Open-World Video Anomaliescited by 49
  20. 2024Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Promptscited by 40
  21. 2021Learning Not to Reconstruct Anomaliescited by 31
  22. 2022Bayesian Nonparametric Submodular Video Partition for Robust Anomaly Detectioncited by 23
  23. 2020Few-Shot Anomaly Detection for Polyp Frames from Colonoscopycited by 19
  24. 2022Consistency-based Self-supervised Learning for Temporal Anomaly Localizationcited by 10

Built on by

Not cited yet.