mlsanityData to 7 Oct 2026

Learning Normal Dynamics in Videos with Meta Prototype Network

arXiv 2104.06689 ↗First posted 14 Apr 2021cs.CVcited by 71

Not on the map. Why?

Abstract (arXiv)

Frame reconstruction (current or future frame) based on Auto-Encoder (AE) is a popular method for video anomaly detection. With models trained on the normal data, the reconstruction errors of anomalous scenes are usually much larger than those of normal ones. Previous methods introduced the memory bank into AE, for encoding diverse normal patterns across the training videos. However, they are memory-consuming and cannot cope with unseen new scenarios in the testing data. In this work, we propose a dynamic prototype unit (DPU) to encode the normal dynamics as prototypes in real time, free from extra memory cost. In addition, we introduce meta-learning to our DPU to form a novel few-shot normalcy learner, namely Meta-Prototype Unit (MPU). It enables the fast adaption capability on new scenes by only consuming a few iterations of update. Extensive experiments are conducted on various benchmarks. The superior performance over the state-of-the-art demonstrates the effectiveness of our method.

Key facts. Cited by 71 papers in the map (data through 7 Oct 2026). Builds on 35 of its 52 references that are in the map. First posted on arXiv 14 Apr 2021.

Builds on

35 of 52 references.

References · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2017Squeeze-and-Excitation Networkscited by 4,763
  5. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  6. 2016Matching Networks for One Shot Learningcited by 2,246
  7. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  8. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  9. 2018Real-world Anomaly Detection in Surveillance Videoscited by 570
  10. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  11. 2019Selective Kernel Networkscited by 401
  12. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
23 more
  1. 2017Residual Attention Network for Image Classificationcited by 385
  2. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 377
  3. 2015Gradient-based Hyperparameter Optimization through Reversible Learningcited by 357
  4. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  5. 2017Meta Networkscited by 268
  6. 2016Learning Temporal Regularity in Video Sequencescited by 254
  7. 2016Unrolled Generative Adversarial Networkscited by 208
  8. 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
  9. 2019Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detectioncited by 171
  10. 2018Latent Space Autoregression for Novelty Detectioncited by 149
  11. 2019Anomaly Detection in Video Sequence with Appearance-Motion Correspondencecited by 118
  12. 2018Learning a Discriminative Feature Network for Semantic Segmentationcited by 114
  13. 2020Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detectioncited by 83
  14. 2020Few-shot Scene-adaptive Anomaly Detectioncited by 62
  15. 2017Abnormal Event Detection in Videos using Spatiotemporal Autoencodercited by 57
  16. 2017Joint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledgecited by 55
  17. 2020Localizing Anomalies from Weakly-Labeled Videoscited by 52
  18. 2017Unmasking the abnormal events in videocited by 48
  19. 2019Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Informationcited by 35
  20. 2018Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackerscited by 34
  21. 2019Future Frame Prediction Using Convolutional VRNN for Anomaly Detectioncited by 27
  22. 2017Robust, Deep and Inductive Anomaly Detectioncited by 24
  23. 2017xUnit: Learning a Spatial Activation Function for Efficient Image Restorationcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 10; 2023: 15; 2024: 19; 2025: 18; 2026: 5.

71 papers.

Sort:

By area:

  1. 2024Harnessing Large Language Models for Training-free Video Anomaly Detectioncited by 85
  2. 2023Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detectioncited by 66
  3. 2023Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detectioncited by 64
  4. 2024Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Modelscited by 55
  5. 2023Video Event Restoration Based on Keyframes for Video Anomaly Detectioncited by 54
  6. 2024Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detectioncited by 49
  7. 2024Advancing Video Anomaly Detection: A Concise Review and a New Datasetcited by 48
  8. 2025Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detectioncited by 47
  9. 2023A New Comprehensive Benchmark for Semi-supervised Video Anomaly Detection and Anticipationcited by 42
  10. 2023Diversity-Measurable Anomaly Detectioncited by 41
  11. 2023Hierarchical Semantic Contrast for Scene-aware Video Anomaly Detectioncited by 39
  12. 2023Anomaly Detection under Distribution Shiftcited by 35
38 more
  1. 2021SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detectioncited by 34
  2. 2022Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detectioncited by 27
  3. 2023Delving into CLIP latent space for Video Anomaly Recognitioncited by 27
  4. 2024Deep Learning for Video Anomaly Detection: A Reviewcited by 27
  5. 2021Deep Anomaly Discovery From Unlabeled Videos via Normality Advantage and Self-Paced Refinementcited by 21
  6. 2024MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detectioncited by 21
  7. 2022Cross-Domain Video Anomaly Detection without Target Domain Adaptationcited by 20
  8. 2022Context Recovery and Knowledge Retrieval: A Novel Two-Stream Framework for Video Anomaly Detectioncited by 18
  9. 2021Learnable Locality-Sensitive Hashing for Video Anomaly Detectioncited by 17
  10. 2025AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLMcited by 15
  11. 2024MissionGNN: Hierarchical Multimodal GNN-based Weakly Supervised Video Anomaly Recognition with Mission-Specific Knowledge Graph Generationcited by 14
  12. 2024Video Anomaly Detection with Motion and Appearance Guided Patch Diffusion Modelcited by 14
  13. 2024Exploiting Structural Consistency of Chest Anatomy for Unsupervised Anomaly Detection in Radiography Imagescited by 13
  14. 2024Context-aware Video Anomaly Detection in Long-Term Datasetscited by 11
  15. 2023SLSG: Industrial Image Anomaly Detection by Learning Better Feature Embeddings and One-Class Classificationcited by 10
  16. 2025MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly Detectioncited by 10
  17. 2023REB: Reducing Biases in Representation for Industrial Anomaly Detectioncited by 9
  18. 2025Towards Visual Discrimination and Reasoning of Real-World Physical Dynamics: Physics-Grounded Anomaly Detectioncited by 9
  19. 2024VideoPatchCore: An Effective Method to Memorize Normality for Video Anomaly Detectioncited by 8
  20. 2025Foundation Models and Transformers for Anomaly Detection: A Surveycited by 8
  21. 2025HiProbe-VAD: Video Anomaly Detection via Hidden States Probing in Tuning-Free Multimodal LLMscited by 8
  22. 2025INP-Former++: Advancing Universal Anomaly Detection via Intrinsic Normal Prototypes and Residual Learningcited by 7
  23. 2024Cross-Domain Learning for Video Anomaly Detection with Limited Supervisioncited by 6
  24. 2024Human-Centric Video Anomaly Detection Through Spatio-Temporal Pose Tokenization and Transformercited by 6
  25. 2024Vision-Language Models Assisted Unsupervised Video Anomaly Detectioncited by 6
  26. 2022Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detectioncited by 5
  27. 2023Multi-level Memory-augmented Appearance-Motion Correspondence Framework for Video Anomaly Detectioncited by 5
  28. 2024Structural Teacher-Student Normality Learning for Multi-Class Anomaly Detection and Localizationcited by 5
  29. 2025A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understandingcited by 5
  30. 2025SmartHome-Bench: A Comprehensive Benchmark for Video Anomaly Detection in Smart Homes Using Multi-Modal Large Language Modelscited by 4
  31. 2025Autoregressive Denoising Score Matching is a Good Video Anomaly Detectorcited by 4
  32. 2025The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLMcited by 4
  33. 2022Object Class Aware Video Anomaly Detection through Image Translationcited by 3
  34. 2024Unveiling Context-Related Anomalies: Knowledge Graph Empowered Decoupling of Scene and Action for Human-Related Video Anomaly Detectioncited by 3
  35. 2024Appearance Blur-driven AutoEncoder and Motion-guided Memory Module for Video Anomaly Detectioncited by 3
  36. 2025Detecting Contextual Anomalies by Discovering Consistent Spatial Regionscited by 3
  37. 2022Language-Assisted Deep Learning for Autistic Behaviors Recognitioncited by 2
  38. 2023Future Video Prediction from a Single Frame for Video Anomaly Detectioncited by 2

50 most cited of 71 All 71 (JSON)