Home > Research > Publications & Outputs > Generalized Video Anomaly Event Detection

Research

Links

Text available via DOI:

View graph of relations

Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models. / Liu, Yang; Yang, Dingkang; Wang, Yan et al.
In: ACM Computing Surveys, Vol. 56, No. 7, 189, 31.07.2024.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Liu, Y, Yang, D, Wang, Y, Liu, J, Liu, J, Boukerche, A, Sun, P & Song, L 2024, 'Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models', ACM Computing Surveys, vol. 56, no. 7, 189. https://doi.org/10.1145/3645101

APA

Liu, Y., Yang, D., Wang, Y., Liu, J., Liu, J., Boukerche, A., Sun, P., & Song, L. (2024). Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models. ACM Computing Surveys, 56(7), Article 189. https://doi.org/10.1145/3645101

Vancouver

Liu Y, Yang D, Wang Y, Liu J, Liu J, Boukerche A et al. Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models. ACM Computing Surveys. 2024 Jul 31;56(7):189. doi: 10.1145/3645101

Author

Liu, Yang ; Yang, Dingkang ; Wang, Yan et al. / Generalized Video Anomaly Event Detection : Systematic Taxonomy and Comparison of Deep Models. In: ACM Computing Surveys. 2024 ; Vol. 56, No. 7.

Bibtex

@article{0c740f4a246243d89f998cf4af3f2568,
title = "Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models",
abstract = "Video Anomaly Detection (VAD) serves as a pivotal technology in the intelligent surveillance systems, enabling the temporal or spatial identification of anomalous events within videos. While existing reviews predominantly concentrate on conventional unsupervised methods, they often overlook the emergence of weakly-supervised and fully-unsupervised approaches. To address this gap, this survey extends the conventional scope of VAD beyond unsupervised methods, encompassing a broader spectrum termed Generalized Video Anomaly Event Detection (GVAED). By skillfully incorporating recent advancements rooted in diverse assumptions and learning frameworks, this survey introduces an intuitive taxonomy that seamlessly navigates through unsupervised, weakly-supervised, supervised and fully-unsupervised VAD methodologies, elucidating the distinctions and interconnections within these research trajectories. In addition, this survey facilitates prospective researchers by assembling a compilation of research resources, including public datasets, available codebases, programming tools, and pertinent literature. Furthermore, this survey quantitatively assesses model performance, delves into research challenges and directions, and outlines potential avenues for future exploration.",
author = "Yang Liu and Dingkang Yang and Yan Wang and Jing Liu and Jun Liu and Azzedine Boukerche and Peng Sun and Liang Song",
year = "2024",
month = jul,
day = "31",
doi = "10.1145/3645101",
language = "English",
volume = "56",
journal = "ACM Computing Surveys",
issn = "0360-0300",
publisher = "Association for Computing Machinery (ACM)",
number = "7",

}

RIS

TY - JOUR

T1 - Generalized Video Anomaly Event Detection

T2 - Systematic Taxonomy and Comparison of Deep Models

AU - Liu, Yang

AU - Yang, Dingkang

AU - Wang, Yan

AU - Liu, Jing

AU - Liu, Jun

AU - Boukerche, Azzedine

AU - Sun, Peng

AU - Song, Liang

PY - 2024/7/31

Y1 - 2024/7/31

N2 - Video Anomaly Detection (VAD) serves as a pivotal technology in the intelligent surveillance systems, enabling the temporal or spatial identification of anomalous events within videos. While existing reviews predominantly concentrate on conventional unsupervised methods, they often overlook the emergence of weakly-supervised and fully-unsupervised approaches. To address this gap, this survey extends the conventional scope of VAD beyond unsupervised methods, encompassing a broader spectrum termed Generalized Video Anomaly Event Detection (GVAED). By skillfully incorporating recent advancements rooted in diverse assumptions and learning frameworks, this survey introduces an intuitive taxonomy that seamlessly navigates through unsupervised, weakly-supervised, supervised and fully-unsupervised VAD methodologies, elucidating the distinctions and interconnections within these research trajectories. In addition, this survey facilitates prospective researchers by assembling a compilation of research resources, including public datasets, available codebases, programming tools, and pertinent literature. Furthermore, this survey quantitatively assesses model performance, delves into research challenges and directions, and outlines potential avenues for future exploration.

AB - Video Anomaly Detection (VAD) serves as a pivotal technology in the intelligent surveillance systems, enabling the temporal or spatial identification of anomalous events within videos. While existing reviews predominantly concentrate on conventional unsupervised methods, they often overlook the emergence of weakly-supervised and fully-unsupervised approaches. To address this gap, this survey extends the conventional scope of VAD beyond unsupervised methods, encompassing a broader spectrum termed Generalized Video Anomaly Event Detection (GVAED). By skillfully incorporating recent advancements rooted in diverse assumptions and learning frameworks, this survey introduces an intuitive taxonomy that seamlessly navigates through unsupervised, weakly-supervised, supervised and fully-unsupervised VAD methodologies, elucidating the distinctions and interconnections within these research trajectories. In addition, this survey facilitates prospective researchers by assembling a compilation of research resources, including public datasets, available codebases, programming tools, and pertinent literature. Furthermore, this survey quantitatively assesses model performance, delves into research challenges and directions, and outlines potential avenues for future exploration.

U2 - 10.1145/3645101

DO - 10.1145/3645101

M3 - Journal article

VL - 56

JO - ACM Computing Surveys

JF - ACM Computing Surveys

SN - 0360-0300

IS - 7

M1 - 189

ER -