mlsanityData to 14 Oct 2026

Learning Event Completeness for Weakly Supervised Video Anomaly Detection

arXiv 2506.13095 ↗First posted 16 Jun 2025cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Weakly supervised video anomaly detection (WS-VAD) is tasked with pinpointing temporal intervals containing anomalous events within untrimmed videos, utilizing only video-level annotations. However, a significant challenge arises due to the absence of dense frame-level annotations, often leading to incomplete localization in existing WS-VAD methods. To address this issue, we present a novel LEC-VAD, Learning Event Completeness for Weakly Supervised Video Anomaly Detection, which features a dual structure designed to encode both category-aware and category-agnostic semantics between vision and language. Within LEC-VAD, we devise semantic regularities that leverage an anomaly-aware Gaussian mixture to learn precise event boundaries, thereby yielding more complete event instances. Besides, we develop a novel memory bank-based prototype learning mechanism to enrich concise text descriptions associated with anomaly-event categories. This innovation bolsters the text's expressiveness, which is crucial for advancing WS-VAD. Our LEC-VAD demonstrates remarkable advancements over the current state-of-the-art methods on two benchmark datasets XD-Violence and UCF-Crime.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 42 of its 63 references that are in the map. First posted on arXiv 16 Jun 2025.

Builds on

42 of 63 references.

References · 42

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  5. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  6. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,619
  7. 2018Real-world Anomaly Detection in Surveillance Videoscited by 577
  8. 2021Prompting Visual-Language Models for Efficient Video Understandingcited by 310
  9. 2016Learning Temporal Regularity in Video Sequencescited by 254
  10. 2020Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervisioncited by 238
  11. 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 230
  12. 2023UniVTG: Towards Unified Video-Language Temporal Groundingcited by 190
30 more
  1. 2019Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detectioncited by 171
  2. 2021MIST: Multiple Instance Self-Training Framework for Video Anomaly Detectioncited by 138
  3. 2023Can I Trust Your Answer? Visually Grounded Video Question Answeringcited by 135
  4. 2023Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrievalcited by 132
  5. 2023VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detectioncited by 123
  6. 2022Generative Cooperative Learning for Unsupervised Video Anomaly Detectioncited by 102
  7. 2023Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detectioncited by 90
  8. 2022MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detectioncited by 89
  9. 2024Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Promptscited by 89
  10. 2020A Survey of Single-Scene Video Anomaly Detectioncited by 88
  11. 2018W-TALC: Weakly-supervised Temporal Activity Localization and Classificationcited by 87
  12. 2020CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detectioncited by 79
  13. 2018AutoLoc: Weakly-supervised Temporal Action Localizationcited by 75
  14. 2022CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detectioncited by 67
  15. 2019GODS: Generalized One-class Discriminative Subspaces for Anomaly Detectioncited by 64
  16. 2023Open-Vocabulary Video Anomaly Detectioncited by 57
  17. 2023Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answeringcited by 51
  18. 2022Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Modelscited by 49
  19. 2024Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detectioncited by 49
  20. 2022Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detectioncited by 47
  21. 2023Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detectioncited by 43
  22. 2024Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Promptscited by 40
  23. 2023Bootstrapping Vision-Language Learning with Decoupled Language Pre-trainingcited by 28
  24. 2022Modality-Aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence Detectioncited by 26
  25. 2023Towards Video Anomaly Retrieval from Video Anomaly Detection: New Benchmarks and Modelcited by 25
  26. 2022Bayesian Nonparametric Submodular Video Partition for Robust Anomaly Detectioncited by 23
  27. 2024Efficient Vision-Language Pre-training by Cluster Maskingcited by 13
  28. 2022Clustering Aided Weakly Supervised Training to Detect Anomalous Events in Surveillance Videoscited by 12
  29. 2023Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approachcited by 10
  30. 2022Locality-aware Attention Network with Discriminative Dynamics Learning for Weakly Supervised Anomaly Detectioncited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Learning to Watch: Active Video Anomaly Understanding via Interleaved Policy Optimizationcited by 4
  2. 2026Weakly Supervised Video Anomaly Detection with Anomaly-Connected Components and Intention Reasoningcited by 3
  3. 2026TD-VAD: Breaking Visual Dependence in Video Anomaly Detection with Text-Driven Learningcited by 2