RefineVAD: Semantic-Guided Feature Recalibration for Weakly Supervised Video Anomaly Detection
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (7) · 5899-5907
DOI: 10.1609/aaai.v40i7.37512 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Junhee Lee und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
Weakly-Supervised Video Anomaly Detection aims to identify anomalous events using only video-level labels, balancing annotation efficiency with practical applicability. However, existing methods often oversimplify the anomaly space by treating all abnormal events as a single category, overlooking the diverse semantic and temporal characteristics intrinsic to real-world anomalies. Inspired by how humans perceive anomalies, by jointly interpreting temporal motion patterns and semantic structures underlying different anomaly types, we propose RefineVAD, a novel framework that mimics this dual-process reasoning. Our framework integrates two core modules. The first, Motion-aware Temporal Attention and Recalibration (MoTAR), estimates motion salience and dynamically adjusts temporal focus via shift-based attention and global Transformer-based modeling. The second, Category-Oriented Refinement (CORE), injects soft anomaly category priors into the representation space by aligning segment-level features with learnable category prototypes through cross-attention. By jointly leveraging temporal dynamics and semantic structure, explicitly models both ``how'' motion evolves and ``what'' semantic category it resembles. Extensive experiments on WVAD benchmark validate the effectiveness of RefineVAD and highlight the importance of integrating semantic context to guide feature refinement toward anomaly-relevant patterns.
Zitieren
APA
Lee, J., Bang, C., Kim, M., & Cho, M. (2026). RefineVAD: Semantic-Guided Feature Recalibration for Weakly Supervised Video Anomaly Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 40(7), 5899-5907. https://doi.org/10.1609/aaai.v40i7.37512
Vancouver
Lee J, Bang C, Kim M, Cho M. RefineVAD: Semantic-Guided Feature Recalibration for Weakly Supervised Video Anomaly Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(7):5899-5907. doi:10.1609/aaai.v40i7.37512
BibTeX
@article{Lee2026,
author = {Lee, Junhee and Bang, ChaeBeen and Kim, MyoungChul and Cho, MyeongAh},
title = {RefineVAD: Semantic-Guided Feature Recalibration for Weakly Supervised Video Anomaly Detection},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {7},
pages = {5899--5907},
doi = {10.1609/aaai.v40i7.37512}
}
EUVIMED