Holistic Representation Learning for Multitask Trajectory Anomaly Detection

Research output: Chapter in Book/Report/Conference proceedingConference paper

2 Citations (Scopus)
59 Downloads (Pure)

Abstract

Video anomaly detection deals with the recognition of abnormal events in videos. Apart from the visual signal, video anomaly detection has also been addressed with the use of skeleton sequences. We propose a holistic representation of skeleton trajectories to learn expected motions across segments at different times. Our approach uses multitask learning to reconstruct any continuous unobserved temporal segment of the trajectory allowing the extrapolation of past or future segments and the interpolation of in-between segments. We use an end-to-end attention-based encoder-decoder. We encode temporally occluded trajectories, jointly learn latent representations of the occluded segments, and reconstruct trajectories based on expected motions across different temporal segments. Extensive experiments on three trajectory-based video anomaly detection datasets show the advantages and effectiveness of our approach with state-of-the-art results on anomaly detection in skeleton trajectories.
Original languageEnglish
Title of host publicationProceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
PublisherIEEE
Pages6729-6739
Number of pages11
ISBN (Print)9798350318920
DOIs
Publication statusPublished - 3 Jan 2024
EventIEEE/CVF Winter Conference on Applications of Computer Vision - Waikoloa, United States
Duration: 4 Jan 20248 Jan 2024
https://wacv2024.thecvf.com/

Publication series

NameProceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024

Conference

ConferenceIEEE/CVF Winter Conference on Applications of Computer Vision
Abbreviated titleWACV
Country/TerritoryUnited States
CityWaikoloa
Period4/01/248/01/24
Internet address

Bibliographical note

Publisher Copyright:
© 2024 IEEE.

Fingerprint

Dive into the research topics of 'Holistic Representation Learning for Multitask Trajectory Anomaly Detection'. Together they form a unique fingerprint.

Cite this