Distribution-Aware Activity Boundary Representation for Online Detection of Action Start in Untrimmed Videos
IEEE Signal Processing Letters · 2024 · 31 · 765-769
DOI: 10.1109/lsp.2024.3352503 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2024. Verfasst von Xuejiao Hu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 29 Literaturangaben.
Abstract (Originalsprache)
The Online Detection of Action Start (ODAS) has attracted the attention of researchers because of its practical applications in areas such as security and emergency response. However, online detection of activity boundaries remains a challenging task due to the inherent ambiguity of boundary definition and the significant imbalance in the number of boundaries and nonboundary points. To address this issue, this study proposes a novel Distribution-aware Activity Boundary Representation (DABR) method that utilizes a continuous probability density function to smooth the probability of moments near activity boundaries. The proposed DABR reduces the penalty for detecting moments near ground-truth boundary points, while increasing the number of samples related to boundary points. Additionally, we introduce a two-stage framework that incorporates class-informed information in temporal localization for more efficient activity boundary localization. Extensive experiments demonstrate that our method achieves state-of-the-art results on two standard datasets, particularly exhibiting a significant improvement of 11.5% at average p-mAP on the THUMOS'14 dataset.
Zitieren
APA
Hu, X., Wang, S., Li, M., Li, Y., & Du, S. (2024). Distribution-Aware Activity Boundary Representation for Online Detection of Action Start in Untrimmed Videos. IEEE Signal Processing Letters, 31, 765-769. https://doi.org/10.1109/lsp.2024.3352503
Vancouver
Hu X, Wang S, Li M, Li Y, Du S. Distribution-Aware Activity Boundary Representation for Online Detection of Action Start in Untrimmed Videos. IEEE Signal Processing Letters. 2024;31:765-769. doi:10.1109/lsp.2024.3352503
BibTeX
@article{Hu2024,
author = {Hu, Xuejiao and Wang, Shijie and Li, Ming and Li, Yang and Du, Sidan},
title = {Distribution-Aware Activity Boundary Representation for Online Detection of Action Start in Untrimmed Videos},
journal = {IEEE Signal Processing Letters},
year = {2024},
volume = {31},
pages = {765--769},
doi = {10.1109/lsp.2024.3352503}
}
EUVIMED