A Revisit of Sparse Coding Based Anomaly Detection in Stacked RNN Framework

By Weixin Luo, Wen Liu, Shenghua Gao. IEEE International Conference on Computer Vision, 2017

831 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/99dff291f260b3cc3ff190106b0c2e3e685223a4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows (2021, methodology): “We conduct unsupervised anomaly detection (imagelevel) and localization (pixel-level segmentation) experiments using the MVTec [4] dataset with factory defects and the STC [22] dataset with surveillance camera videos.”
Future Frame Prediction for Anomaly Detection - A New Baseline (2017, methodology): “In this section, we evaluate our proposed method as well as the functionalities of different components on three publicly available anomaly detection datasets, including the CUHK Avenue dataset [20], the UCSD Pedestrian dataset [23] and the ShanghaiTech dataset [22].”
Anomaly Detection in Video via Self-Supervised and Multi-Task Learning (2020, methodology): “While some frameworks, such as [27, 33, 40, 41, 47], approach the problem from a global (frame-level) perspective, methods such as [7, 11, 21, 19, 28, 29, 31, 32, 44, 46, 64] extract features at a local level, e.g . by considering spatio-temporal cubes.”
Latent Space Autoregression for Novelty Detection (2018, methodology): “Therefore, prior works tackle such problem by following principles derived from the unsupervised learning paradigm [9, 34, 11, 23, 27].”
A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction (2021, methodology): “, UCSD Ped2 [34], CUHK Avenue [29] and ShanghaiTech [32].”
A Review on Deep Learning Techniques for Video Prediction (2020, neutral): “[101] 2019 [45], [192], [193] cycleGAN [115], [119], [120], [194], [195] RGB RGB X `1, LoG,AL R ? ? ? 7 7”
Memorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly Detection (2019, methodology): “To show the effectiveness of the proposed memory module, we compare the proposed MemAE with many well-designed reconstruction based state-of-the-art methods including AE methods with 2D [11] and 3D convolution [45] (AE-Conv2D and AE-Conv3D), a temporally-coherent sparse coding method (TST) [26], a s”
Self-Training Multi-Sequence Learning with Transformer for Weakly Supervised Video Anomaly Detection (2022, methodology): “We conduct sufﬁcient experiments on the ShanghaiTech, UCF-Crime, and XD-Violence datasets.”
Visual Memorability for Robotic Interestingness via Unsupervised Online Learning (2020, background): “We notice that sparsity is also mentioned in [42,27,13], while it is designed for different objectives using different strategies.”
MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection (2021, methodology): “For the ShanghaiTech dataset results in Table 2, our MIST far outperforms other RGB-based methods [23, 32, 35, 27], which validates the capacity of MIST.”
Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning (2021, methodology): “Although one-class classifiers (OCCs, also called unsupervised anomaly detection) trained exclusively with normal videos have been explored in this context [15,17,27,30,46, 47, 76], the best performing approaches explore a weaklysupervised setup using training samples with video-level label annotati”
AnomalyNet: An Anomaly Detection Network for Video Surveillance (2019, methodology): “suitable metric [5], [7], which measures the performance by changing different thresholds.”
Anomaly Detection in Video Sequence With Appearance-Motion Correspondence (2019, background): “…AMDN (double fusion) [51] - 0.908 ConvLSTM-AE [27] 0.770 0.881 DeepAppearance [42] 0.846 - FRCN action [14] - 0.922 TSC [28] 0.806 0.910 Stacked RNN [28] 0.817 0.922 AbnormalGAN [37] - 0.935 GrowingGas [46] - 0.941 Future frame prediction [25] 0.851 0.954 Our proposed method 0.869 0.962 Table 1.”
Learning Memory-Guided Normality for Anomaly Detection (2020, methodology): “Methods Ped2 [21] Avenue [24] Shanghai [26]”
Sub-Image Anomaly Detection with Deep Pyramid Correspondences (2020, methodology): “The ShanghaiTech Campus dataset [23] - a dataset simulating a surveillance setting where cameras observe a busy campus and the objective is to detect anomalous objects and activities such as ﬁghts.”
Student-Teacher Feature Pyramid Matching for Anomaly Detection (2021, result): “It reports very competitive results on the MVTec anomaly detection dataset, and more results on ShanghaiTech Campus (STC) [23] and CIFAR-10 [18] are presented in the supplementary material.”
Graph Convolutional Label Noise Cleaner: Train a Plug-And-Play Action Classifier for Anomaly Detection (2019, background): “Sparse reconstruction [41, 31, 13, 67] is also another popular approach for usual pattern modeling.”
Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos (2019, methodology): “The ShanghaiTech Campus dataset [20] is considered one of the most comprehensive and realistic datasets for video anomaly detection currently available.”