Look at Adjacent Frames: Video Anomaly Detection without Offline Training
Not on the map. Why?
Abstract (arXiv)
We propose a solution to detect anomalous events in videos without the need to train a model offline. Specifically, our solution is based on a randomly-initialized multilayer perceptron that is optimized online to reconstruct video frames, pixel-by-pixel, from their frequency information. Based on the information shifts between adjacent frames, an incremental learner is used to update parameters of the multilayer perceptron after observing each frame, thus allowing to detect anomalous events along the video stream. Traditional solutions that require no offline training are limited to operating on videos with only a few abnormal frames. Our solution breaks this limit and achieves strong performance on benchmark datasets.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 39 of its 55 references that are in the map. First posted on arXiv 27 Jul 2022.
Builds on
39 of 55 references.
References · 39
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
- 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
- 2018On First-Order Meta-Learning Algorithmscited by 1,003
- 2018Real-world Anomaly Detection in Surveillance Videoscited by 570
- 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
- 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
- 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
- 2016Learning Temporal Regularity in Video Sequencescited by 254
- 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 240
- 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 226
27 more
- 2019Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detectioncited by 171
- 2018Latent Space Autoregression for Novelty Detectioncited by 149
- 2020Anomaly Detection in Video via Self-Supervised and Multi-Task Learningcited by 147
- 2021MIST: Multiple Instance Self-Training Framework for Video Anomaly Detectioncited by 137
- 2021A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Predictioncited by 129
- 2019Anomaly Detection in Video Sequence with Appearance-Motion Correspondencecited by 118
- 2020Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigmcited by 115
- 2018Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Videocited by 110
- 2019Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videoscited by 103
- 2019Graph Embedded Pose Clustering for Anomaly Detectioncited by 95
- 2020A Survey of Single-Scene Video Anomaly Detectioncited by 88
- 2020Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detectioncited by 83
- 2017Abnormal Event Detection in Videos using Generative Adversarial Netscited by 82
- 2020CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detectioncited by 79
- 2015Learning Deep Representations of Appearance and Motion for Anomalous Event Detectioncited by 75
- 2021Learning Normal Dynamics in Videos with Meta Prototype Networkcited by 71
- 2020Few-shot Scene-adaptive Anomaly Detectioncited by 62
- 2017Joint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledgecited by 55
- 2020Exploring Spatial-Temporal Multi-Frequency Analysis for High-Fidelity and Temporal-Consistency Video Predictioncited by 52
- 2020Continual Learning for Anomaly Detection in Surveillance Videoscited by 49
- 2017Unmasking the abnormal events in videocited by 48
- 2019Motion-Aware Feature for Improved Video Anomaly Detectioncited by 48
- 2016A Discriminative Framework for Anomaly Detection in Large Videoscited by 25
- 2021Image/Video Deep Anomaly Detection: A Surveycited by 10
- 2020Video Anomaly Detection by Estimating Likelihood of Representationscited by 9
- 2021A Modular and Unified Framework for Detecting and Localizing Video Anomaliescited by 6
- 2022Video Anomaly Detection via Prediction Network with Enhanced Spatio-Temporal Memory Exchangecited by 5
Built on by
Citing papers per year: 2022: 1.
1 paper.