mlsanityData to 7 Oct 2026

MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detection

arXiv 2211.15098 ↗First posted 28 Nov 2022cs.CVcited by 87

Not on the map. Why?

Abstract (arXiv)

Weakly supervised detection of anomalies in surveillance videos is a challenging task. Going beyond existing works that have deficient capabilities to localize anomalies in long videos, we propose a novel glance and focus network to effectively integrate spatial-temporal information for accurate anomaly detection. In addition, we empirically found that existing approaches that use feature magnitudes to represent the degree of anomalies typically ignore the effects of scene variations, and hence result in sub-optimal performance due to the inconsistency of feature magnitudes across scenes. To address this issue, we propose the Feature Amplification Mechanism and a Magnitude Contrastive Loss to enhance the discriminativeness of feature magnitudes for detecting anomalies. Experimental results on two large-scale benchmarks UCF-Crime and XD-Violence manifest that our method outperforms state-of-the-art approaches.

Key facts. Cited by 87 papers in the map (data through 7 Oct 2026). Builds on 35 of its 49 references that are in the map. First posted on arXiv 28 Nov 2022.

Builds on

35 of 49 references.

References · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  7. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,609
  8. 2021Video Swin Transformercited by 1,090
  9. 2020Pre-Trained Image Processing Transformercited by 891
  10. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  11. 2020A Survey on Visual Transformercited by 653
  12. 2018Real-world Anomaly Detection in Surveillance Videoscited by 570
23 more
  1. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  2. 2019Deep Learning for Anomaly Detection: A Surveycited by 357
  3. 2018Video Action Transformer Networkcited by 316
  4. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  5. 2016Learning Temporal Regularity in Video Sequencescited by 254
  6. 2020Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervisioncited by 235
  7. 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 226
  8. 2019Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detectioncited by 171
  9. 2021MIST: Multiple Instance Self-Training Framework for Video Anomaly Detectioncited by 137
  10. 2021A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Predictioncited by 129
  11. 2018Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Videocited by 110
  12. 2022Generative Cooperative Learning for Unsupervised Video Anomaly Detectioncited by 102
  13. 2020CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detectioncited by 79
  14. 2020LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attentioncited by 65
  15. 2019GODS: Generalized One-class Discriminative Subspaces for Anomaly Detectioncited by 64
  16. 2020Few-shot Scene-adaptive Anomaly Detectioncited by 62
  17. 2019Motion-Aware Feature for Improved Video Anomaly Detectioncited by 48
  18. 2021Weakly Supervised Video Anomaly Detection via Center-guided Discriminative Learningcited by 44
  19. 2020SCT: Set Constrained Temporal Transformer for Set Supervised Action Segmentationcited by 39
  20. 2021Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Videocited by 32
  21. 2018Subspace Support Vector Data Descriptioncited by 31
  22. 2020RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decodercited by 31
  23. 2021Cleaning Label Noise with Clusters for Minimally Supervised Anomaly Detectioncited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 11; 2024: 24; 2025: 28; 2026: 23.

87 papers.

Sort:

By area:

  1. 2024Harnessing Large Language Models for Training-free Video Anomaly Detectioncited by 85
  2. 2024Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularitycited by 66
  3. 2024Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLMcited by 63
  4. 2024Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detectioncited by 49
  5. 2024Advancing Video Anomaly Detection: A Concise Review and a New Datasetcited by 48
  6. 2023Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challengescited by 42
  7. 2023Vision-Based Traffic Accident Detection and Anticipation: A Surveycited by 31
  8. 2023Delving into CLIP latent space for Video Anomaly Recognitioncited by 27
  9. 2024Deep Learning for Video Anomaly Detection: A Reviewcited by 27
  10. 2023Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detectioncited by 25
  11. 2024VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Modelscited by 24
  12. 2025VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuningcited by 24
38 more
  1. 2023TeD-SPAD: Temporal Distinctiveness for Self-supervised Privacy-preservation for video Anomaly Detectioncited by 23
  2. 2024Learnable Expansion of Graph Operators for Multi-Modal Feature Fusioncited by 22
  3. 2023Weakly-Supervised Video Anomaly Detection with Snippet Anomalous Attentioncited by 15
  4. 2025VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Treecited by 15
  5. 2025Handling Out-of-Distribution Data: A Surveycited by 14
  6. 2025Flashback: Memory-Driven Zero-shot, Real-time Video Anomaly Detectioncited by 12
  7. 2025MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly Detectioncited by 10
  8. 2025Towards Visual Discrimination and Reasoning of Real-World Physical Dynamics: Physics-Grounded Anomaly Detectioncited by 9
  9. 2025A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysiscited by 9
  10. 2025HiProbe-VAD: Video Anomaly Detection via Hidden States Probing in Tuning-Free Multimodal LLMscited by 8
  11. 2025Unlocking Vision-Language Models for Video Anomaly Detection via Fine-Grained Promptingcited by 8
  12. 2024Anomaly Detection for People with Visual Impairments Using an Egocentric 360-Degree Cameracited by 7
  13. 2025Aligning Effective Tokens with Video Anomaly in Large Language Modelscited by 7
  14. 2024Cross-Domain Learning for Video Anomaly Detection with Limited Supervisioncited by 6
  15. 2024Towards Adaptive Human-centric Video Anomaly Detection: A Comprehensive Framework and A New Benchmarkcited by 6
  16. 2024Human-Centric Video Anomaly Detection Through Spatio-Temporal Pose Tokenization and Transformercited by 6
  17. 2025Mixture of Experts Guided by Gaussian Splatters Matters: A new Approach to Weakly-Supervised Video Anomaly Detectioncited by 6
  18. 2025ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognitioncited by 5
  19. 2025Pistachio: Towards Synthetic, Balanced, and Long-Form Video Anomaly Benchmarkscited by 5
  20. 2023Human-Scene Network: A Novel Baseline with Self-rectifying Loss for Weakly supervised Video Anomaly Detectioncited by 4
  21. 2025STEAD: Spatio-Temporal Efficient Anomaly Detection for Time and Compute Sensitive Applicationscited by 4
  22. 2025The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLMcited by 4
  23. 2026Instance-Aligned Captions for Explainable Video Anomaly Detectioncited by 4
  24. 2024Distilling Aggregated Knowledge for Weakly-Supervised Video Anomaly Detectioncited by 3
  25. 2024Unveiling Context-Related Anomalies: Knowledge Graph Empowered Decoupling of Scene and Action for Human-Related Video Anomaly Detectioncited by 3
  26. 2025Rethinking Metrics and Benchmarks of Video Anomaly Detectioncited by 3
  27. 2025Learning Event Completeness for Weakly Supervised Video Anomaly Detectioncited by 3
  28. 2026Weakly Supervised Video Anomaly Detection with Anomaly-Connected Components and Intention Reasoningcited by 3
  29. 2022Weakly Supervised Video Anomaly Detection Based on Cross-Batch Clustering Guidancecited by 2
  30. 2024Learn Suspected Anomalies from Event Prompts for Video Anomaly Detectioncited by 2
  31. 2025FrameShield: Adversarially Robust Video Anomaly Detectioncited by 2
  32. 2026Steering and Rectifying Latent Representation Manifolds in Frozen Multi-modal LLMs for Video Anomaly Detectioncited by 2
  33. 2026SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hyperspherecited by 2
  34. 2026MemoVAD: Resource-Efficient Video Anomaly Detection via Dynamic Semantic Memory in Edge Computing Scenarioscited by 2
  35. 2023AnoOnly: Semi-Supervised Anomaly Detection with the Only Loss on Anomaliescited by 1
  36. 2023A Lightweight Video Anomaly Detection Model with Weak Supervision and Adaptive Instance Selectioncited by 1
  37. 2024TreeMIL: A Multi-instance Learning Framework for Time Series Anomaly Detection with Inexact Supervisioncited by 1
  38. 2024uTRAND: Unsupervised Anomaly Detection in Traffic Trajectoriescited by 1

50 most cited of 87 All 87 (JSON)