Scaled Background Swap: Video Augmentation for Action Quality Assessment with Background Debiasing
ACM Transactions on Multimedia Computing, Communications, and Applications · 31.08.2025 · 21 (8) · 1-18
DOI: 10.1145/3737461 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 13.08.2025. Verfasst von Xin Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 55 Literaturangaben.
Abstract (Originalsprache)
Action quality assessment (AQA) has become crucial in video analysis, finding wide applications in various domains, such as healthcare and sports. A significant challenge faced by AQA is the background bias due to the dominance of the background in videos. Especially, the background bias tends to overshadow subtle foreground differences, which is crucial for precise action evaluation. To address the background bias issue, we propose a novel data augmentation method named Scaled Background Swap. First, the background regions between different video samples are swapped to guide models focus toward the dynamic foreground regions and mitigate its sensitivity to the background during training. Second, the video’s foreground region is upscaled to further enhance models’ attention to the critical foreground action information for AQA tasks. In particular, the proposed Scaled Background Swap method can effectively improve models’ accuracy and generalization by prioritizing foreground motion and swapping backgrounds. It can be flexibly applied with various video analysis models. Extensive experiments on AQA benchmarks demonstrate that Scaled Background Swap method achieves better performance than baselines. Specifically, the Spearman’s rank correlation on datasets AQA-7 and MTL-AQA reaches 0.8870 and 0.9526, respectively. The code is available at: https://github.com/Emy-cv/Scaled-Background Swap.
Zitieren
APA
Zhang, X., Feng, H., Hossain, M. S., Chen, Y., Wang, H., & Yin, Y. (2025). Scaled Background Swap: Video Augmentation for Action Quality Assessment with Background Debiasing. ACM Transactions on Multimedia Computing, Communications, and Applications, 21(8), 1-18. https://doi.org/10.1145/3737461
Vancouver
Zhang X, Feng H, Hossain MS, Chen Y, Wang H, Yin Y. Scaled Background Swap: Video Augmentation for Action Quality Assessment with Background Debiasing. ACM Transactions on Multimedia Computing, Communications, and Applications. 2025;21(8):1-18. doi:10.1145/3737461
BibTeX
@article{Zhang2025,
author = {Zhang, Xin and Feng, Hongzhi and Hossain, M. Shamim and Chen, Yinzhuo and Wang, Hongbo and Yin, Yuyu},
title = {Scaled Background Swap: Video Augmentation for Action Quality Assessment with Background Debiasing},
journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
year = {2025},
volume = {21},
number = {8},
pages = {1--18},
doi = {10.1145/3737461}
}
EUVIMED