mlsanityData to 14 Oct 2026

A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction

arXiv 2108.06852 ↗First posted 16 Aug 2021cs.CVcited by 129

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose HF2-VAD, a Hybrid framework that integrates Flow reconstruction and Frame prediction seamlessly to handle Video Anomaly Detection. Firstly, we design the network of ML-MemAE-SC (Multi-Level Memory modules in an Autoencoder with Skip Connections) to memorize normal patterns for optical flow reconstruction so that abnormal events can be sensitively identified with larger flow reconstruction errors. More importantly, conditioned on the reconstructed flows, we then employ a Conditional Variational Autoencoder (CVAE), which captures the high correlation between video frame and optical flow, to predict the next frame given several previous frames. By CVAE, the quality of flow reconstruction essentially influences that of frame prediction. Therefore, poorly reconstructed optical flows of abnormal events further deteriorate the quality of the final predicted future frame, making the anomalies more detectable. Experimental results demonstrate the effectiveness of the proposed method. Code is available at hrefhttps://github.com/LiUzHiAn/hf2vadhttps://github.com/LiUzHiAn/hf2vad.

Key facts. Cited by 129 papers in the map (data through 14 Oct 2026). Builds on 24 of its 55 references that are in the map. First posted on arXiv 16 Aug 2021.

Builds on

24 of 55 references.

References · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  3. 2013Auto-Encoding Variational Bayescited by 4,053
  4. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  5. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,204
  6. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 784
  7. 2018Real-world Anomaly Detection in Surveillance Videoscited by 577
  8. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 564
  9. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  10. 2015Learning Deconvolution Network for Semantic Segmentationcited by 365
  11. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  12. 2016Learning Temporal Regularity in Video Sequencescited by 254
12 more
  1. 2018A Variational U-Net for Conditional Appearance and Shape Generationcited by 124
  2. 2019Anomaly Detection in Video Sequence with Appearance-Motion Correspondencecited by 118
  3. 2019Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videoscited by 104
  4. 2020Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Eventscited by 70
  5. 2019ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removalcited by 51
  6. 2021A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localizationcited by 45
  7. 2019RIS-GAN: Explore Residual and Illumination with Generative Adversarial Networks for Shadow Removalcited by 35
  8. 2019Future Frame Prediction Using Convolutional VRNN for Anomaly Detectioncited by 27
  9. 2021Dual Graph Convolutional Networks with Transformer and Curriculum Learning for Image Captioningcited by 27
  10. 2018Video Anomaly Detection and Localization via Gaussian Mixture Fully Convolutional Variational Autoencodercited by 21
  11. 2021CRD-CGAN: Category-Consistent and Relativistic Constraints for Diverse Text-to-Image Generationcited by 10
  12. 2020Decoupled Appearance and Motion Learning for Efficient Anomaly Detection in Surveillance Videocited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 5; 2022: 20; 2023: 25; 2024: 35; 2025: 30; 2026: 14.

129 papers.

Sort:

By area:

  1. 2021Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detectioncited by 119
  2. 2021UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detectioncited by 93
  3. 2023Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detectioncited by 90
  4. 2022MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detectioncited by 89
  5. 2024Harnessing Large Language Models for Training-free Video Anomaly Detectioncited by 87
  6. 2024Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularitycited by 70
  7. 2024Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLMcited by 64
  8. 2022Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzlescited by 62
  9. 2022Normalizing Flows for Human Pose Anomaly Detectioncited by 60
  10. 2023Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Modelscited by 59
  11. 2023Open-Vocabulary Video Anomaly Detectioncited by 57
  12. 2024Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Modelscited by 57
38 more
  1. 2022Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detectioncited by 47
  2. 2022SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detectioncited by 45
  3. 2023Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detectioncited by 43
  4. 2023A New Comprehensive Benchmark for Semi-supervised Video Anomaly Detection and Anticipationcited by 42
  5. 2023Diversity-Measurable Anomaly Detectioncited by 41
  6. 2023Hierarchical Semantic Contrast for Scene-aware Video Anomaly Detectioncited by 39
  7. 2023Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectorscited by 37
  8. 2021SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detectioncited by 34
  9. 2022Self-Supervised Masked Convolutional Transformer Block for Anomaly Detectioncited by 34
  10. 2022Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Spacecited by 32
  11. 2022Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detectioncited by 27
  12. 2023Delving into CLIP latent space for Video Anomaly Recognitioncited by 27
  13. 2024Deep Learning for Video Anomaly Detection: A Reviewcited by 27
  14. 2023MEMTO: Memory-guided Transformer for Multivariate Time Series Anomaly Detectioncited by 26
  15. 2021Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detectioncited by 22
  16. 2023BatchNorm-based Weakly Supervised Video Anomaly Detectioncited by 22
  17. 2024MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detectioncited by 22
  18. 2024Networking Systems for Video Anomaly Detection: A Tutorial and Surveycited by 21
  19. 2022Cross-Domain Video Anomaly Detection without Target Domain Adaptationcited by 20
  20. 2022EVAL: Explainable Video Anomaly Localizationcited by 19
  21. 2022Context Recovery and Knowledge Retrieval: A Novel Two-Stream Framework for Video Anomaly Detectioncited by 18
  22. 2024Video Anomaly Detection in 10 Years: A Survey and Outlookcited by 18
  23. 2021Learnable Locality-Sensitive Hashing for Video Anomaly Detectioncited by 17
  24. 2022Social Interpretable Tree for Pedestrian Trajectory Predictioncited by 16
  25. 2023Weakly-Supervised Video Anomaly Detection with Snippet Anomalous Attentioncited by 15
  26. 2024Gazing Into Missteps: Leveraging Eye-Gaze for Unsupervised Mistake Detection in Egocentric Videos of Skilled Human Activitiescited by 15
  27. 2024MissionGNN: Hierarchical Multimodal GNN-based Weakly Supervised Video Anomaly Recognition with Mission-Specific Knowledge Graph Generationcited by 14
  28. 2024Video Anomaly Detection with Motion and Appearance Guided Patch Diffusion Modelcited by 14
  29. 2024Exploiting Structural Consistency of Chest Anatomy for Unsupervised Anomaly Detection in Radiography Imagescited by 13
  30. 2025Anomize: Better Open Vocabulary Video Anomaly Detectioncited by 13
  31. 2025Modeling Multiple Normal Action Representations for Error Detection in Procedural Taskscited by 12
  32. 2024Context-aware Video Anomaly Detection in Long-Term Datasetscited by 11
  33. 2025MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly Detectioncited by 11
  34. 2022Multi-Contextual Predictions with Vision Transformer for Video Anomaly Detectioncited by 10
  35. 2023Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approachcited by 10
  36. 2025A Physical Coherence Benchmark for Evaluating Video Generation Models via Optical Flow-guided Frame Predictioncited by 10
  37. 2025Towards Visual Discrimination and Reasoning of Real-World Physical Dynamics: Physics-Grounded Anomaly Detectioncited by 10
  38. 2024Text-Driven Traffic Anomaly Detection with Temporal High-Frequency Modeling in Driving Videoscited by 9

50 most cited of 129 All 129 (JSON)