mlsanityData to 7 Oct 2026

Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection

arXiv 2112.03649 ↗First posted 7 Dec 2021cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

Anomaly detection in surveillance videos is challenging and important for ensuring public security. Different from pixel-based anomaly detection methods, pose-based methods utilize highly-structured skeleton data, which decreases the computational burden and also avoids the negative impact of background noise. However, unlike pixel-based methods, which could directly exploit explicit motion features such as optical flow, pose-based methods suffer from the lack of alternative dynamic representation. In this paper, a novel Motion Embedder (ME) is proposed to provide a pose motion representation from the probability perspective. Furthermore, a novel task-specific Spatial-Temporal Transformer (STT) is deployed for self-supervised pose sequence reconstruction. These two modules are then integrated into a unified framework for pose regularity learning, which is referred to as Motion Prior Regularity Learner (MoPRL). MoPRL achieves the state-of-the-art performance by an average improvement of 4.7% AUC on several challenging datasets. Extensive experiments validate the versatility of each proposed module.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 49 of its 79 references that are in the map. First posted on arXiv 7 Dec 2021.

Builds on

49 of 79 references.

References · 49

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  8. 2020End-to-End Object Detection with Transformerscited by 7,384
  9. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  10. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  11. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  12. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
37 more
  1. 2018YOLOv3: An Incremental Improvementcited by 2,652
  2. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  3. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,609
  4. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  5. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  6. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  7. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  8. 2021Video Swin Transformercited by 1,090
  9. 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 899
  10. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 852
  11. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  12. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 780
  13. 2018Real-world Anomaly Detection in Surveillance Videoscited by 570
  14. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  15. 2017Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?cited by 551
  16. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  17. 2019Deep Learning for Anomaly Detection: A Surveycited by 357
  18. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  19. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  20. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  21. 2016Learning Temporal Regularity in Video Sequencescited by 254
  22. 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 226
  23. 2020Anomaly Detection in Video via Self-Supervised and Multi-Task Learningcited by 147
  24. 2021A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Predictioncited by 129
  25. 2019Anomaly Detection in Video Sequence with Appearance-Motion Correspondencecited by 118
  26. 2020Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigmcited by 115
  27. 2021Temporal Context Aggregation Network for Temporal Action Proposal Refinementcited by 111
  28. 2018Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Videocited by 110
  29. 2019Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videoscited by 103
  30. 2018Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identificationcited by 96
  31. 2019Graph Embedded Pose Clustering for Anomaly Detectioncited by 95
  32. 2018Pose Flow: Efficient Online Pose Trackingcited by 80
  33. 2020CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detectioncited by 79
  34. 2020Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Eventscited by 70
  35. 2019Multi-timescale Trajectory Prediction for Abnormal Human Activity Detectioncited by 59
  36. 2021Convolutional Transformer based Dual Discriminator Generative Adversarial Networks for Video Anomaly Detectioncited by 31
  37. 2018Cascaded Pyramid Mining Network for Weakly Supervised Temporal Action Localizationcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 10; 2025: 5; 2026: 4.

22 papers.

Sort:

By area:

  1. 2024Advancing Video Anomaly Detection: A Concise Review and a New Datasetcited by 48
  2. 2024Deep Learning for Video Anomaly Detection: A Reviewcited by 27
  3. 2024An Exploratory Study on Human-Centric Video Anomaly Detection through Variational Autoencoders and Trajectory Predictioncited by 19
  4. 2023A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognitioncited by 14
  5. 2024Evaluating the Effectiveness of Video Anomaly Detection in the Wild: Online Learning and Inference for Real-world Deploymentcited by 7
  6. 2024DA-Flow: Dual Attention Normalizing Flow for Skeleton-based Video Anomaly Detectioncited by 7
  7. 2024Towards Adaptive Human-centric Video Anomaly Detection: A Comprehensive Framework and A New Benchmarkcited by 6
  8. 2024Human-Centric Video Anomaly Detection Through Spatio-Temporal Pose Tokenization and Transformercited by 6
  9. 2024Vision-Language Models Assisted Unsupervised Video Anomaly Detectioncited by 6
  10. 2024Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detectioncited by 6
  11. 2025MoFM: A Large-Scale Human Motion Foundation Modelcited by 5
  12. 2025The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLMcited by 4
10 more
  1. 2025A Survey on Video Anomaly Detection via Deep Learning: Human, Vehicle, and Environmentcited by 4
  2. 2024Unveiling Context-Related Anomalies: Knowledge Graph Empowered Decoupling of Scene and Action for Human-Related Video Anomaly Detectioncited by 3
  3. 2025ALFred: An Active Learning Framework for Real-world Semi-supervised Anomaly Detection with Adaptive Thresholdscited by 3
  4. 2026From Offline to Periodic Adaptation for Pose-Based Shoplifting Detection in Real-world Retail Securitycited by 3
  5. 2023Human Kinematics-inspired Skeleton-based Video Anomaly Detectioncited by 1
  6. 2023A Lightweight Video Anomaly Detection Model with Weak Supervision and Adaptive Instance Selectioncited by 1
  7. 2025Action Hints: Semantic Typicality and Context Uniqueness for Generalizable Skeleton-based Video Anomaly Detectioncited by 1
  8. 2026Are Multimodal LLMs Ready for Surveillance? A Reality Check on Zero-Shot Anomaly Detection in the Wildcited by 1
  9. 2026From Frames to Events: Rethinking Evaluation in Human-Centric Video Anomaly Detectioncited by 1
  10. 2026VQ-VAD: Vector-quantized Motion Representation Learning for Human-centric Video Anomaly Detectioncited by 0