mlsanityData to 7 Oct 2026

Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection

arXiv 2303.12369 ↗First posted 22 Mar 2023cs.CVcited by 64

Not on the map. Why?

Abstract (arXiv)

Weakly Supervised Video Anomaly Detection (WSVAD) is challenging because the binary anomaly label is only given on the video level, but the output requires snippet-level predictions. So, Multiple Instance Learning (MIL) is prevailing in WSVAD. However, MIL is notoriously known to suffer from many false alarms because the snippet-level detector is easily biased towards the abnormal snippets with simple context, confused by the normality with the same bias, and missing the anomaly with a different pattern. To this end, we propose a new MIL framework: Unbiased MIL (UMIL), to learn unbiased anomaly features that improve WSVAD. At each MIL training iteration, we use the current detector to divide the samples into two groups with different context biases: the most confident abnormal/normal snippets and the rest ambiguous ones. Then, by seeking the invariant features across the two sample groups, we can remove the variant context biases. Extensive experiments on benchmarks UCF-Crime and TAD demonstrate the effectiveness of our UMIL. Our code is provided at https://github.com/ktr-hubrt/UMIL.

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). Builds on 27 of its 49 references that are in the map. First posted on arXiv 22 Mar 2023.

Builds on

27 of 49 references.

References · 27

  1. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  2. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  3. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428
  4. 2018Real-world Anomaly Detection in Surveillance Videoscited by 570
  5. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  6. 2022Expanding Language-Image Pretrained Models for General Video Recognitioncited by 320
  7. 2016Learning Temporal Regularity in Video Sequencescited by 254
  8. 2020Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervisioncited by 235
  9. 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 226
  10. 2019Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detectioncited by 171
  11. 2020Understanding Self-Training for Gradual Domain Adaptationcited by 149
  12. 2021Cycle Self-Training for Domain Adaptationcited by 120
15 more
  1. 2020Interventional Few-Shot Learningcited by 112
  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. 2015Learning Deep Representations of Appearance and Motion for Anomalous Event Detectioncited by 75
  5. 2021Learning Normal Dynamics in Videos with Meta Prototype Networkcited by 71
  6. 2019GODS: Generalized One-class Discriminative Subspaces for Anomaly Detectioncited by 64
  7. 2020Localizing Anomalies from Weakly-Labeled Videoscited by 52
  8. 2017Unmasking the abnormal events in videocited by 48
  9. 2019Motion-Aware Feature for Improved Video Anomaly Detectioncited by 48
  10. 2021Transporting Causal Mechanisms for Unsupervised Domain Adaptationcited by 38
  11. 2016Plug-and-Play CNN for Crowd Motion Analysis: An Application in Abnormal Event Detectioncited by 32
  12. 2018Subspace Support Vector Data Descriptioncited by 31
  13. 2016A Discriminative Framework for Anomaly Detection in Large Videoscited by 25
  14. 2015Real-Time Anomaly Detection and Localization in Crowded Scenescited by 20
  15. 2021Global Information Guided Video Anomaly Detectioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 21; 2025: 23; 2026: 14.

64 papers.

Sort:

By area:

  1. 2023VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detectioncited by 121
  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. 2023Open-Vocabulary Video Anomaly Detectioncited by 57
  5. 2024Video Anomaly Detection and Explanation via Large Language Modelscited by 45
  6. 2023Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detectioncited by 43
  7. 2024Deep Learning for Video Anomaly Detection: A Reviewcited by 27
  8. 2023Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detectioncited by 25
  9. 2024VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Modelscited by 24
  10. 2024Video Anomaly Detection in 10 Years: A Survey and Outlookcited by 18
  11. 2023Weakly-Supervised Video Anomaly Detection with Snippet Anomalous Attentioncited by 15
  12. 2024Gazing Into Missteps: Leveraging Eye-Gaze for Unsupervised Mistake Detection in Egocentric Videos of Skilled Human Activitiescited by 15
38 more
  1. 2025VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Treecited by 15
  2. 2025Anomize: Better Open Vocabulary Video Anomaly Detectioncited by 13
  3. 2024Privacy-Preserving Video Anomaly Detection: A Surveycited by 11
  4. 2024Exploring What Why and How: A Multifaceted Benchmark for Causation Understanding of Video Anomalycited by 9
  5. 2025Towards Visual Discrimination and Reasoning of Real-World Physical Dynamics: Physics-Grounded Anomaly Detectioncited by 9
  6. 2025Anomaly Detection and Generation with Diffusion Models: A Surveycited by 8
  7. 2024GlanceVAD: Exploring Glance Supervision for Label-efficient Video Anomaly Detectioncited by 7
  8. 2024Vision-Language Models Assisted Unsupervised Video Anomaly Detectioncited by 6
  9. 2024Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detectioncited by 6
  10. 2025Mixture of Experts Guided by Gaussian Splatters Matters: A new Approach to Weakly-Supervised Video Anomaly Detectioncited by 6
  11. 2024Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detectioncited by 5
  12. 2025Aligning First, Then Fusing: A Novel Weakly Supervised Multimodal Violence Detection Methodcited by 5
  13. 2025A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understandingcited by 5
  14. 2025Multi-Instance Partial-Label Learning with Margin Adjustmentcited by 4
  15. 2025The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLMcited by 4
  16. 2025Rethinking Metrics and Benchmarks of Video Anomaly Detectioncited by 3
  17. 2026Weakly Supervised Video Anomaly Detection with Anomaly-Connected Components and Intention Reasoningcited by 3
  18. 2023Learning on Bandwidth Constrained Multi-Source Data with MIMO-inspired DPP MAP Inferencecited by 2
  19. 2024Learn Suspected Anomalies from Event Prompts for Video Anomaly Detectioncited by 2
  20. 2024View-Invariant Pixelwise Anomaly Detection in Multi-object Scenes with Adaptive View Synthesiscited by 2
  21. 2024Multimodal Attention-Enhanced Feature Fusion-based Weekly Supervised Anomaly Violence Detectioncited by 2
  22. 2024A Lightweight Dual-Branch System for Weakly-Supervised Video Anomaly Detection on Consumer Edge Devicescited by 2
  23. 2025The Role of Video Generation in Enhancing Data-Limited Action Understandingcited by 2
  24. 2025Learning from Majority Label: A Novel Problem in Multi-class Multiple-Instance Learningcited by 2
  25. 2025torchmil: A PyTorch-based library for deep Multiple Instance Learningcited by 2
  26. 2025FrameShield: Adversarially Robust Video Anomaly Detectioncited by 2
  27. 2025VADER: Towards Causal Video Anomaly Understanding with Relation-Aware Large Language Modelscited by 2
  28. 2026PPGuide: Steering Diffusion Policies with Performance Predictive Guidancecited by 2
  29. 2024TreeMIL: A Multi-instance Learning Framework for Time Series Anomaly Detection with Inexact Supervisioncited by 1
  30. 2024Identifying Spatio-Temporal Drivers of Extreme Eventscited by 1
  31. 2025ProDisc-VAD: An Efficient System for Weakly-Supervised Anomaly Detection in Video Surveillance Applicationscited by 1
  32. 2025Uncertainty-Weighted Fusion of Image and Synthetic Event for Video Anomaly Detectioncited by 1
  33. 2025Just Dance with π! A Poly-modal Inductor for Weakly-supervised Video Anomaly Detectioncited by 1
  34. 2025CADE: Continual Weakly-supervised Video Anomaly Detection with Ensemblescited by 1
  35. 2026PrismVAU: Prompt-Refined Inference System for Multimodal Video Anomaly Understandingcited by 1
  36. 2026Benchmarking Compact VLMs for Clip-Level Surveillance Anomaly Detection Under Weak Supervisioncited by 1
  37. 2024BCR-Net: Boundary-Category Refinement Network for Weakly Semi-Supervised X-Ray Prohibited Item Detection with Pointscited by 0
  38. 2024Injecting Explainability and Lightweight Design into Weakly Supervised Video Anomaly Detection Systemscited by 0

50 most cited of 64 All 64 (JSON)