Self-supervised Sparse Representation for Video Anomaly Detection

2022-10-23 · ECCV 2022 2022 10 · Jhih-Ciang Wu*, He-Yen Hsieh*, Ding-Jie Chen, Chiou-Shann Fuh, Tyng-Luh Liu

Video anomaly detection (VAD) aims at localizing unexpected actions or activities in a video sequence. Existing mainstream VAD techniques are based on either the one-class formulation, which assumes all training data are normal, or weakly-supervised, which requires only video-level normal/anomaly labels. To establish a unified approach to solving the two VAD settings, we introduce a self-supervised sparse representation (S3R) framework that models the concept of anomaly at feature level by exploring the synergy between dictionary-based representation and self-supervised learning. With the learned dictionary, S3R facilitates two coupled modules, en-Normal and de-Normal, to reconstruct snippet-level features and filter out normal-event features. The self-supervised techniques also enable generating samples of pseudo normal/anomaly to train the anomaly detector. We demonstrate with extensive experiments that S3R achieves new state-of-the-art performances on popular benchmark datasets for both one-class and weakly-supervised VAD tasks. Our code is publicly available at https://github.com/louisYen/S3R.

📄 PDF Abstract BibTeX

Code (1)

louisYen/S3R 공식 구현 pytorch

Tasks

Anomaly Detection Anomaly Detection In Surveillance Videos Self-Supervised Learning Weakly-supervised Video Anomaly Detection

Self-Supervised Representation Learning for Visual Anomaly Detection

2020-06-17 · Rabia Ali, Muhammad Umar Karim Khan, Chong Min Kyung

Self-supervised learning allows for better utilization of unlabelled data. The feature representation obtained by self-supervision can be used in downstream tasks such as classification, object detection, segmentation, a…

Anomaly Detection General Classification object-detection Object Detection+4

MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection

2021-04-04 · CVPR 2021 1 · Jia-Chang Feng, Fa-Ting Hong, Wei-Shi Zheng

Weakly supervised video anomaly detection (WS-VAD) is to distinguish anomalies from normal events based on discriminative representations. Most existing works are limited in insufficient video representations. In this wo…

Anomaly Detection Anomaly Detection In Surveillance Videos Pseudo Label Weakly-supervised Video Anomaly Detection

Modeling Representation of Videos for Anomaly Detection using Deep Learning: A Review

2015-05-04 · Yong Shean Chong, Yong Haur Tay

This review article surveys the current progresses made toward video-based anomaly detection. We address the most fundamental aspect for video anomaly detection, that is, video feature representation. Much research works…

Action Recognition Anomaly Detection Deep Learning Temporal Action Localization+1

Hyperspectral Anomaly Detection with Self-Supervised Anomaly Prior

2024-04-20 · Yidan Liu, Weiying Xie, Kai Jiang, Jiaqing Zhang 외

The majority of existing hyperspectral anomaly detection (HAD) methods use the low-rank representation (LRR) model to separate the background and anomaly components, where the anomaly component is optimized by handcrafte…

Anomaly Detection Self-Supervised Learning

Human-Scene Network: A Novel Baseline with Self-rectifying Loss for Weakly supervised Video Anomaly Detection

2023-01-19 · Snehashis Majhi, Rui Dai, Quan Kong, Lorenzo Garattoni 외

Video anomaly detection in surveillance systems with only video-level labels (i.e. weakly-supervised) is challenging. This is due to, (i) the complex integration of human and scene based anomalies comprising of subtle an…

Anomaly Detection Video Anomaly Detection Weakly-supervised Video Anomaly Detection