Projects per year
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 language | English |
---|---|
Title of host publication | Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) |
Publisher | IEEE |
Pages | 6729-6739 |
Number of pages | 11 |
ISBN (Print) | 9798350318920 |
DOIs | |
Publication status | Published - 3 Jan 2024 |
Event | IEEE/CVF Winter Conference on Applications of Computer Vision - Waikoloa, United States Duration: 4 Jan 2024 → 8 Jan 2024 https://wacv2024.thecvf.com/ |
Publication series
Name | Proceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024 |
---|
Conference
Conference | IEEE/CVF Winter Conference on Applications of Computer Vision |
---|---|
Abbreviated title | WACV |
Country/Territory | United States |
City | Waikoloa |
Period | 4/01/24 → 8/01/24 |
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.Projects
- 1 Active
-
FWOSB140: DUST: Designing Interpretable and Efficient Deep Unfolding Sparse Transformers for Multimodal Image Processing and Generation
Deligiannis, N. & De Weerdt, B.
1/11/22 → 31/10/26
Project: Fundamental