2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · 2023 · 49 citations · 42 references
ComputingComputer ScienceComputer VisionData MiningMachine LearningAnomaly DetectionRepresentation LearningModel Performance AnalysisModel Performance EvaluationRanking LossTriplet LossVideo Anomaly DetectionVideo-based SupervisionWeakly Supervised Anomaly Detection
Weakly supervised Video Anomaly Detection (wVAD) aims to distinguish anomalies from normal events based on video-level supervision. Most existing works utilize Multiple Instance Learning (MIL) with ranking loss to tackle this task. These methods, however, rely on noisy predictions from a MIL-based classifier for target instance selection in ranking loss, degrading model performance. To overcome this problem, we propose Normality Guided Multiple Instance Learning (NG-MIL) framework, which encodes diverse normal patterns from noise-free normal videos into prototypes for constructing a similarity-based classifier. By ensembling predictions of two classifiers, our method could refine the anomaly scores, reducing training instability from weak labels. Moreover, we introduce normality clustering and normality guided triplet loss constraining inner bag instances to boost the effect of NG-MIL and increase the discriminability of classifiers. Extensive experiments on three public datasets (ShanghaiTech, UCF-Crime, XD-Violence) demonstrate that our method is comparable to or better than existing weakly supervised methods, achieving state-of-the-art results.
42
Adam: A Method for Stochastic Optimization
Diederik P. Kingma, Jimmy Ba · UvA-DARE (University of Amsterdam) · 2014 · 84.8K citations · Full text
Least squares quantization in PCM
Sheelagh Lloyd · IEEE Transactions on Information Theory · 1982 · 15.6K citations · Full text
Large-Scale Video Classification with Convolutional Neural Networks
Andrej Karpathy, George Toderici, Sanketh Shetty et al. · 2014 · 6.3K citations
Estimating the Support of a High-Dimensional Distribution
Bernhard Schölkopf, John Platt, John Shawe‐Taylor et al. · Neural Computation · 2001 · 5.9K citations
Support Vector Data Description
David M. J. Tax, Robert P. W. Duin · Machine Learning · 2003 · 3.5K citations · Full text