Vectorized Evidential Learning for Weakly-Supervised Temporal Action Localization
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2023-12 · 45 (12) · 15949-15963
DOI: 10.1109/tpami.2023.3311447 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023-12. Verfasst von Junyu Gao und 2 weiteren Autor:innen. Die Arbeit wurde bisher 85-mal zitiert (Crossref) und nennt 93 Literaturangaben. Gefördert von: National Key Research and Development Plan of China, National Natural Science Foundation of China, Beijing Natural Science Foundation.
Abstract (Originalsprache)
With the explosive growth of videos, weakly-supervised temporal action localization (WS-TAL) task has become a promising research direction in pattern analysis and machine learning. WS-TAL aims to detect and localize action instances with only video-level labels during training. Modern approaches have achieved impressive progress via powerful deep neural networks. However, robust and reliable WS-TAL remains challenging and underexplored due to considerable uncertainty caused by weak supervision, noisy evaluation environment, and unknown categories in the open world. To this end, we propose a new paradigm, named vectorized evidential learning (VEL), to explore local-to-global evidence collection for facilitating model performance. Specifically, a series of learnable meta-action units (MAUs) are automatically constructed, which serve as fundamental elements constituting diverse action categories. Since the same meta-action unit can manifest as distinct action components within different action categories, we leverage MAUs and category representations to dynamically and adaptively learn action components and action-component relations. After performing uncertainty estimation at both category-level and unit-level, the local evidence from action components is accumulated and optimized under the Subject Logic theory. Extensive experiments on the regular, noisy, and open-set settings of three popular benchmarks show that VEL consistently obtains more robust and reliable action localization performance than state-of-the-arts.
Förderung
- National Key Research and Development Plan of China
- National Natural Science Foundation of China
- Beijing Natural Science Foundation
- Open Research Projects of Zhejiang Lab
Zitieren
APA
Gao, J., Chen, M., & Xu, C. (2023). Vectorized Evidential Learning for Weakly-Supervised Temporal Action Localization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(12), 15949-15963. https://doi.org/10.1109/tpami.2023.3311447
Vancouver
Gao J, Chen M, Xu C. Vectorized Evidential Learning for Weakly-Supervised Temporal Action Localization. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(12):15949-15963. doi:10.1109/tpami.2023.3311447
BibTeX
@article{Gao2023,
author = {Gao, Junyu and Chen, Mengyuan and Xu, Changsheng},
title = {Vectorized Evidential Learning for Weakly-Supervised Temporal Action Localization},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2023},
volume = {45},
number = {12},
pages = {15949--15963},
doi = {10.1109/tpami.2023.3311447}
}
EUVIMED