mlsanityData to 7 Oct 2026

Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning

arXiv 2101.10030 ↗First posted 25 Jan 2021cs.CVcited by 226

Not on the map. Why?

Abstract (arXiv)

Anomaly detection with weakly supervised video-level labels is typically formulated as a multiple instance learning (MIL) problem, in which we aim to identify snippets containing abnormal events, with each video represented as a bag of video snippets. Although current methods show effective detection performance, their recognition of the positive instances, i.e., rare abnormal snippets in the abnormal videos, is largely biased by the dominant negative instances, especially when the abnormal events are subtle anomalies that exhibit only small differences compared with normal events. This issue is exacerbated in many methods that ignore important video temporal dependencies. To address this issue, we introduce a novel and theoretically sound method, named Robust Temporal Feature Magnitude learning (RTFM), which trains a feature magnitude learning function to effectively recognise the positive instances, substantially improving the robustness of the MIL approach to the negative instances from abnormal videos. RTFM also adapts dilated convolutions and self-attention mechanisms to capture long- and short-range temporal dependencies to learn the feature magnitude more faithfully. Extensive experiments show that the RTFM-enabled MIL model (i) outperforms several state-of-the-art methods by a large margin on four benchmark data sets (ShanghaiTech, UCF-Crime, XD-Violence and UCSD-Peds) and (ii) achieves significantly improved subtle anomaly discriminability and sample efficiency. Code is available at https://github.com/tianyu0207/RTFM.

Key facts. Cited by 226 papers in the map (data through 7 Oct 2026). Builds on 48 of its 84 references that are in the map. First posted on arXiv 25 Jan 2021.

Builds on

48 of 84 references.

References · 48

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  4. 2017Non-local Neural Networkscited by 2,290
  5. 2017The Kinetics Human Action Video Datasetcited by 1,894
  6. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  7. 2018Real-world Anomaly Detection in Surveillance Videoscited by 570
  8. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  9. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  10. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  11. 2020Exploring Self-attention for Image Recognitioncited by 313
  12. 2019Deep Semi-Supervised Anomaly Detectioncited by 290
36 more
  1. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  2. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  3. 2016Learning Temporal Regularity in Video Sequencescited by 254
  4. 2020Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervisioncited by 235
  5. 2020Classification-Based Anomaly Detection for General Datacited by 210
  6. 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
  7. 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
  8. 2014Learning Fine-grained Image Similarity with Deep Rankingcited by 189
  9. 2019Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detectioncited by 171
  10. 2019Deep Anomaly Detection with Deviation Networkscited by 152
  11. 2018Latent Space Autoregression for Novelty Detectioncited by 149
  12. 2020Anomaly Detection in Video via Self-Supervised and Multi-Task Learningcited by 147
  13. 2019Anomaly Detection in Video Sequence with Appearance-Motion Correspondencecited by 118
  14. 2018Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Videocited by 110
  15. 2019Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videoscited by 103
  16. 2019Graph Embedded Pose Clustering for Anomaly Detectioncited by 95
  17. 2020A Survey of Single-Scene Video Anomaly Detectioncited by 88
  18. 2020Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detectioncited by 83
  19. 2017Abnormal Event Detection in Videos using Generative Adversarial Netscited by 82
  20. 2018Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detectioncited by 79
  21. 2020CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detectioncited by 79
  22. 2015Learning Deep Representations of Appearance and Motion for Anomalous Event Detectioncited by 75
  23. 2020Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Eventscited by 70
  24. 2019GODS: Generalized One-class Discriminative Subspaces for Anomaly Detectioncited by 64
  25. 2017Joint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledgecited by 55
  26. 2020Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Imagescited by 52
  27. 2017Unmasking the abnormal events in videocited by 48
  28. 2019Motion-Aware Feature for Improved Video Anomaly Detectioncited by 48
  29. 2016Plug-and-Play CNN for Crowd Motion Analysis: An Application in Abnormal Event Detectioncited by 32
  30. 2018Subspace Support Vector Data Descriptioncited by 31
  31. 2016A Discriminative Framework for Anomaly Detection in Large Videoscited by 25
  32. 2020A Self-Reasoning Framework for Anomaly Detection Using Video-Level Labelscited by 23
  33. 2020Few-Shot Anomaly Detection for Polyp Frames from Colonoscopycited by 19
  34. 2019Unsupervised Dual Adversarial Learning for Anomaly Detection in Colonoscopy Video Framescited by 14
  35. 2020SpotNet: Self-Attention Multi-Task Network for Object Detectioncited by 14
  36. 2019Attention Guided Anomaly Localization in Imagescited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 23; 2023: 37; 2024: 49; 2025: 53; 2026: 55.

226 papers.

Sort:

By area:

  1. 2023VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detectioncited by 121
  2. 2022Generative Cooperative Learning for Unsupervised Video Anomaly Detectioncited by 102
  3. 2021UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detectioncited by 91
  4. 2023Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detectioncited by 88
  5. 2022MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detectioncited by 87
  6. 2024Harnessing Large Language Models for Training-free Video Anomaly Detectioncited by 85
  7. 2021Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenescited by 83
  8. 2021Explainable Deep Few-shot Anomaly Detection with Deviation Networkscited by 69
  9. 2022CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detectioncited by 67
  10. 2024Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularitycited by 66
  11. 2023Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detectioncited by 64
  12. 2024Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLMcited by 63
38 more
  1. 2023Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Modelscited by 59
  2. 2023Open-Vocabulary Video Anomaly Detectioncited by 57
  3. 2024Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detectioncited by 49
  4. 2024Advancing Video Anomaly Detection: A Concise Review and a New Datasetcited by 48
  5. 2022Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detectioncited by 47
  6. 2024Hawk: Learning to Understand Open-World Video Anomaliescited by 47
  7. 2021Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical Imagescited by 45
  8. 2022SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detectioncited by 45
  9. 2024Video Anomaly Detection and Explanation via Large Language Modelscited by 45
  10. 2023Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detectioncited by 43
  11. 2023Hierarchical Semantic Contrast for Scene-aware Video Anomaly Detectioncited by 39
  12. 2023Delving into CLIP latent space for Video Anomaly Recognitioncited by 27
  13. 2024Deep Learning for Video Anomaly Detection: A Reviewcited by 27
  14. 2022Modality-Aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence Detectioncited by 26
  15. 2022Towards Open Set Video Anomaly Detectioncited by 26
  16. 2023Towards Video Anomaly Retrieval from Video Anomaly Detection: New Benchmarks and Modelcited by 25
  17. 2023Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detectioncited by 25
  18. 2024VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Modelscited by 24
  19. 2025VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuningcited by 24
  20. 2021Self-supervised Pseudo Multi-class Pre-training for Unsupervised Anomaly Detection and Segmentation in Medical Imagescited by 23
  21. 2022Bayesian Nonparametric Submodular Video Partition for Robust Anomaly Detectioncited by 23
  22. 2023Exploring Diffusion Models for Unsupervised Video Anomaly Detectioncited by 23
  23. 2023TeD-SPAD: Temporal Distinctiveness for Self-supervised Privacy-preservation for video Anomaly Detectioncited by 23
  24. 2021Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detectioncited by 22
  25. 2023Weakly Supervised Anomaly Detection: A Surveycited by 22
  26. 2023BatchNorm-based Weakly Supervised Video Anomaly Detectioncited by 22
  27. 2024Learnable Expansion of Graph Operators for Multi-Modal Feature Fusioncited by 22
  28. 2021Deep Anomaly Discovery From Unlabeled Videos via Normality Advantage and Self-Paced Refinementcited by 21
  29. 2024Networking Systems for Video Anomaly Detection: A Tutorial and Surveycited by 21
  30. 2022Contrastive Transformer-based Multiple Instance Learning for Weakly Supervised Polyp Frame Detectioncited by 20
  31. 2022Cross-Domain Video Anomaly Detection without Target Domain Adaptationcited by 20
  32. 2022CHAD: Charlotte Anomaly Datasetcited by 18
  33. 2023Unsupervised Video Anomaly Detection with Diffusion Models Conditioned on Compact Motion Representationscited by 18
  34. 2024Video Anomaly Detection in 10 Years: A Survey and Outlookcited by 18
  35. 2025UCF-Crime-DVS: A Novel Event-Based Dataset for Video Anomaly Detection with Spiking Neural Networkscited by 18
  36. 2024Collaborative Learning of Anomalies with Privacy (CLAP) for Unsupervised Video Anomaly Detection: A New Baselinecited by 17
  37. 2023Weakly-Supervised Video Anomaly Detection with Snippet Anomalous Attentioncited by 15
  38. 2023Holistic Representation Learning for Multitask Trajectory Anomaly Detectioncited by 15

50 most cited of 226 All 226 (JSON)