Enhancing Few-Shot Video Anomaly Detection with Key-Frame Selection and Relational Cross Transformers

Ahmed Fakhry, Jong Taek Lee

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Detecting illegal activities using video anomaly detection is an enormous challenge in security and surveillance. The lack of labeled instances for anomalous actions poses a significant obstacle to existing learning techniques, and determining the optimal data representation that captures the essential features and patterns vital for detecting anomalies proves to be exceedingly difficult. We have developed a few-shot video anomaly detection method, FewVAD, which employs a key-frame selection module and spatial-temporal relational modeling to extract pertinent features and reduce temporal redundancy from lengthy surveillance recordings. We have evaluated our method on two popular surveillance datasets, UCF-Crime and XD-Violence, and compared its performance against established few-shot models and other unsupervised and weakly supervised learning video anomaly detection models. Our model has attained an accuracy of 41.7% and 54.3% for 5-way 5-shot few-shot configuration on the UCF-Crime and XD-Violence datasets, respectively. Furthermore, it has obtained an AUC score of 86.60% for the 2-way anomaly detection task on the UCFCrime dataset. FewVAD achieves a milestone in few-shot video anomaly detection, competing strongly with current weakly-supervised and unsupervised VAD methods.

Original languageEnglish
Title of host publicationAVSS 2024 - 20th IEEE International Conference on Advanced Video and Signal-Based Surveillance
PublisherInstitute of Electrical and Electronics Engineers Inc.
Edition2024
ISBN (Electronic)9798350374285
DOIs
StatePublished - 2024
Event20th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2024 - Niagara Falls, Canada
Duration: 15 Jul 202416 Jul 2024

Conference

Conference20th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2024
Country/TerritoryCanada
CityNiagara Falls
Period15/07/2416/07/24

Fingerprint

Dive into the research topics of 'Enhancing Few-Shot Video Anomaly Detection with Key-Frame Selection and Relational Cross Transformers'. Together they form a unique fingerprint.

Cite this