Adaptive Temporal Action Localization in Video
Electronics · 30.06.2025 · 14 (13) · 2645
DOI: 10.3390/electronics14132645 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 30.06.2025. Verfasst von Zhiyu Xu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Temporal action localization aims to identify the boundaries of the action of interest in a video. Most existing methods take a two-stage approach: first, identify a set of action proposals; then, based on this set, determine the accurate temporal locations of the action of interest. However, the diversely distributed semantics of a video over time have not been well considered, which could compromise the localization performance, especially for ubiquitous short actions or events (e.g., a fall in healthcare and a traffic violation in surveillance). To address this problem, we propose a novel deep learning architecture, namely an adaptive template-guided self-attention network, to characterize the proposals adaptively with their relevant frames. An input video is segmented into temporal frames, within which the spatio-temporal patterns are formulated by a global–Local Transformer-based encoder. Each frame is associated with a number of proposals of different lengths as their starting frame. Learnable templates for proposals of different lengths are introduced, and each template guides the sampling for proposals with a specific length. It formulates the probabilities for a proposal to form the representation of certain spatio-temporal patterns from its relevant temporal frames. Therefore, the semantics of a proposal can be formulated in an adaptive manner, and a feature map of all proposals can be appropriately characterized. To estimate the IoU of these proposals with ground truth actions, a two-level scheme is introduced. A shortcut connection is also utilized to refine the predictions by using the convolutions of the feature map from coarse to fine. Comprehensive experiments on two benchmark datasets demonstrate the state-of-the-art performance of our proposed method: 32.6% mAP@IoU 0.7 on THUMOS-14 and 9.35% mAP@IoU 0.95 on ActivityNet-1.3.
Zitieren
APA
Xu, Z., Lu, Z., Ding, Y., Tian, L., & Liu, S. (2025). Adaptive Temporal Action Localization in Video. Electronics, 14(13), 2645. https://doi.org/10.3390/electronics14132645
Vancouver
Xu Z, Lu Z, Ding Y, Tian L, Liu S. Adaptive Temporal Action Localization in Video. Electronics. 2025;14(13):2645. doi:10.3390/electronics14132645
BibTeX
@article{Xu2025,
author = {Xu, Zhiyu and Lu, Zhuqiang and Ding, Yong and Tian, Liwei and Liu, Suping},
title = {Adaptive Temporal Action Localization in Video},
journal = {Electronics},
year = {2025},
volume = {14},
number = {13},
pages = {2645},
doi = {10.3390/electronics14132645}
}
EUVIMED