CLASP: Cross-modal Salient Anchor-based Semantic Propagation for Weakly-supervised Dense Audio-Visual Event Localization
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (16) · 13674-13682
DOI: 10.1609/aaai.v40i16.38374 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Jinxing Zhou und 5 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref).
Abstract (Originalsprache)
The Dense Audio-Visual Event Localization (DAVEL) task aims to temporally localize events in untrimmed videos that occur simultaneously in both the audio and visual modalities. This paper explores DAVEL under a new and more challenging weakly-supervised setting (W-DAVEL task), where only video-level event labels are provided and the temporal boundaries of each event are unknown. We address W-DAVEL by exploiting cross-modal salient anchors, which are defined as reliable timestamps that are well predicted under weak supervision and exhibit highly consistent event semantics across audio and visual modalities. Specifically, we propose a Mutual Event Agreement Evaluation module, which generates an agreement score by measuring the discrepancy between the predicted audio and visual event classes. Then, the agreement score is utilized in a Cross-modal Salient Anchor Identification module, which identifies the audio and visual anchor features through global-video and local temporal window identification mechanisms. The anchor features after multimodal integration are fed into an Anchor-based Temporal Propagation module to enhance event semantic encoding in the original temporal audio and visual features, facilitating better temporal localization under weak supervision. We establish benchmarks for W-DAVEL on both the UnAV-100 and ActivityNet1.3 datasets. Extensive experiments demonstrate that our method achieves state-of-the-art performance.
Zitieren
APA
Zhou, J., Zhou, Z., Zhou, Y., Mao, Y., Duan, Z., & Guo, D. (2026). CLASP: Cross-modal Salient Anchor-based Semantic Propagation for Weakly-supervised Dense Audio-Visual Event Localization. Proceedings of the AAAI Conference on Artificial Intelligence, 40(16), 13674-13682. https://doi.org/10.1609/aaai.v40i16.38374
Vancouver
Zhou J, Zhou Z, Zhou Y, Mao Y, Duan Z, Guo D. CLASP: Cross-modal Salient Anchor-based Semantic Propagation for Weakly-supervised Dense Audio-Visual Event Localization. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(16):13674-13682. doi:10.1609/aaai.v40i16.38374
BibTeX
@article{Zhou2026,
author = {Zhou, Jinxing and Zhou, Ziheng and Zhou, Yanghao and Mao, Yuxin and Duan, Zhangling and Guo, Dan},
title = {CLASP: Cross-modal Salient Anchor-based Semantic Propagation for Weakly-supervised Dense Audio-Visual Event Localization},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {16},
pages = {13674--13682},
doi = {10.1609/aaai.v40i16.38374}
}
EUVIMED