mlsanityData to 14 Oct 2026

Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzles

arXiv 2207.10172 ↗First posted 20 Jul 2022cs.CVcited by 62

Not on the map. Why?

Abstract (arXiv)

Video Anomaly Detection (VAD) is an important topic in computer vision. Motivated by the recent advances in self-supervised learning, this paper addresses VAD by solving an intuitive yet challenging pretext task, i.e., spatio-temporal jigsaw puzzles, which is cast as a multi-label fine-grained classification problem. Our method exhibits several advantages over existing works: 1) the spatio-temporal jigsaw puzzles are decoupled in terms of spatial and temporal dimensions, responsible for capturing highly discriminative appearance and motion features, respectively; 2) full permutations are used to provide abundant jigsaw puzzles covering various difficulty levels, allowing the network to distinguish subtle spatio-temporal differences between normal and abnormal events; and 3) the pretext task is tackled in an end-to-end manner without relying on any pre-trained models. Our method outperforms state-of-the-art counterparts on three public benchmarks. Especially on ShanghaiTech Campus, the result is superior to reconstruction and prediction-based methods by a large margin.

Key facts. Cited by 62 papers in the map (data through 14 Oct 2026). Builds on 37 of its 63 references that are in the map. First posted on arXiv 20 Jul 2022.

Builds on

37 of 63 references.

References · 37

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2018YOLOv3: An Incremental Improvementcited by 2,659
  6. 2017Non-local Neural Networkscited by 2,293
  7. 2017The Kinetics Human Action Video Datasetcited by 1,909
  8. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  9. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  10. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
  11. 2016Colorful Image Colorizationcited by 1,114
  12. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,066
25 more
  1. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 564
  2. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
  3. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  4. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  5. 2016Learning Temporal Regularity in Video Sequencescited by 254
  6. 2017Unsupervised Representation Learning by Sorting Sequencescited by 221
  7. 2020SpeedNet: Learning the Speediness in Videoscited by 171
  8. 2021VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examplescited by 154
  9. 2018Self-Supervised Video Representation Learning with Space-Time Cubic Puzzlescited by 149
  10. 2020Anomaly Detection in Video via Self-Supervised and Multi-Task Learningcited by 148
  11. 2021A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Predictioncited by 129
  12. 2019Anomaly Detection in Video Sequence with Appearance-Motion Correspondencecited by 118
  13. 2018Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Videocited by 111
  14. 2019Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videoscited by 104
  15. 2020A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Videocited by 86
  16. 2020Video Representation Learning by Recognizing Temporal Transformationscited by 83
  17. 2020Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Eventscited by 70
  18. 2020Robust Unsupervised Video Anomaly Detection by Multi-Path Frame Predictioncited by 42
  19. 2018Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognitioncited by 40
  20. 2021Convolutional Transformer based Dual Discriminator Generative Adversarial Networks for Video Anomaly Detectioncited by 31
  21. 2021Learning Not to Reconstruct Anomaliescited by 31
  22. 2019Future Frame Prediction Using Convolutional VRNN for Anomaly Detectioncited by 27
  23. 2018Video Anomaly Detection and Localization via Gaussian Mixture Fully Convolutional Variational Autoencodercited by 21
  24. 2017Limiting the Reconstruction Capability of Generative Neural Network using Negative Learningcited by 16
  25. 2020Towards Anomaly Detection in Dashcam Videoscited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 13; 2024: 25; 2025: 12; 2026: 9.

62 papers.

Sort:

By area:

  1. 2022Normalizing Flows for Human Pose Anomaly Detectioncited by 60
  2. 2023Open-Vocabulary Video Anomaly Detectioncited by 57
  3. 2024Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Modelscited by 57
  4. 2024Advancing Video Anomaly Detection: A Concise Review and a New Datasetcited by 49
  5. 2023A New Comprehensive Benchmark for Semi-supervised Video Anomaly Detection and Anticipationcited by 42
  6. 2023Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectorscited by 37
  7. 2024Deep Learning for Video Anomaly Detection: A Reviewcited by 27
  8. 2023Towards Video Anomaly Retrieval from Video Anomaly Detection: New Benchmarks and Modelcited by 25
  9. 2024MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detectioncited by 22
  10. 2024An Exploratory Study on Human-Centric Video Anomaly Detection through Variational Autoencoders and Trajectory Predictioncited by 19
  11. 2022Context Recovery and Knowledge Retrieval: A Novel Two-Stream Framework for Video Anomaly Detectioncited by 18
  12. 2025AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLMcited by 15
38 more
  1. 2024Solving Masked Jigsaw Puzzles with Diffusion Vision Transformerscited by 11
  2. 2024Privacy-Preserving Video Anomaly Detection: A Surveycited by 11
  3. 2023Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approachcited by 10
  4. 2024Graph-Jigsaw Conditioned Diffusion Model for Skeleton-based Video Anomaly Detectioncited by 9
  5. 2024VideoPatchCore: An Effective Method to Memorize Normality for Video Anomaly Detectioncited by 8
  6. 2025ComplexVAD: Detecting Interaction Anomalies in Videocited by 8
  7. 2025VAGU & GtS: LLM-Based Benchmark and Framework for Joint Video Anomaly Grounding and Understandingcited by 8
  8. 2023Unveiling the Unseen: A Comprehensive Survey on Explainable Anomaly Detection in Images and Videoscited by 7
  9. 2024Evaluating the Effectiveness of Video Anomaly Detection in the Wild: Online Learning and Inference for Real-world Deploymentcited by 7
  10. 2024DA-Flow: Dual Attention Normalizing Flow for Skeleton-based Video Anomaly Detectioncited by 7
  11. 2024Anomaly Detection for People with Visual Impairments Using an Egocentric 360-Degree Cameracited by 7
  12. 2025Sequential keypoint density estimator: an overlooked baseline of skeleton-based video anomaly detectioncited by 7
  13. 2024Towards Adaptive Human-centric Video Anomaly Detection: A Comprehensive Framework and A New Benchmarkcited by 6
  14. 2024Human-Centric Video Anomaly Detection Through Spatio-Temporal Pose Tokenization and Transformercited by 6
  15. 2024Vision-Language Models Assisted Unsupervised Video Anomaly Detectioncited by 6
  16. 2023Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation for Anomaly Detectioncited by 5
  17. 2024Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detectioncited by 5
  18. 2025MoFM: A Large-Scale Human Motion Foundation Modelcited by 5
  19. 2025Autoregressive Denoising Score Matching is a Good Video Anomaly Detectorcited by 4
  20. 2025The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLMcited by 4
  21. 2025A Survey on Video Anomaly Detection via Deep Learning: Human, Vehicle, and Environmentcited by 4
  22. 2022Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillationcited by 3
  23. 2024IPAD: Industrial Process Anomaly Detection Datasetcited by 3
  24. 2024Unveiling Context-Related Anomalies: Knowledge Graph Empowered Decoupling of Scene and Action for Human-Related Video Anomaly Detectioncited by 3
  25. 2025Self-Supervised Learning for Image Segmentation: A Comprehensive Surveycited by 3
  26. 2025ALFred: An Active Learning Framework for Real-world Semi-supervised Anomaly Detection with Adaptive Thresholdscited by 3
  27. 2026From Offline to Periodic Adaptation for Pose-Based Shoplifting Detection in Real-world Retail Securitycited by 3
  28. 2026Bounding-Box Trajectories Matter for Video Anomaly Detectioncited by 3
  29. 2023Unsupervised Video Anomaly Detection for Stereotypical Behaviours in Autismcited by 2
  30. 2024Frequency-Guided Multi-Level Human Action Anomaly Detection with Normalizing Flowscited by 2
  31. 2024CKNN: Cleansed k-Nearest Neighbor for Unsupervised Video Anomaly Detectioncited by 2
  32. 2023Divide and Conquer in Video Anomaly Detection: A Comprehensive Review and New Approachcited by 1
  33. 2023Human Kinematics-inspired Skeleton-based Video Anomaly Detectioncited by 1
  34. 2023Beyond the Benchmark: Detecting Diverse Anomalies in Videoscited by 1
  35. 2024Interactive Explainable Anomaly Detection for Industrial Settingscited by 1
  36. 2024Identifying Spatio-Temporal Drivers of Extreme Eventscited by 1
  37. 2025Action Hints: Semantic Typicality and Context Uniqueness for Generalizable Skeleton-based Video Anomaly Detectioncited by 1
  38. 2023Reasonable Anomaly Detection in Long Sequencescited by 0

50 most cited of 62 All 62 (JSON)