Self-Supervised Sub-Action Parsing Network for Semi-Supervised Action Quality Assessment
IEEE Transactions on Image Processing · 2024 · 33 · 6057-6070
DOI: 10.1109/tip.2024.3468870 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2024. Verfasst von Kumie Gedamu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 61 Literaturangaben. Gefördert von: Ministry of Science and Technology of China Foreign Young Talents Program, Sichuan Science and Technology Program, National Natural Science Foundation of China.
Abstract (Originalsprache)
Semi-supervised Action Quality Assessment (AQA) using limited labeled and massive unlabeled samples to achieve high-quality assessment is an attractive but challenging task. The main challenge relies on how to exploit solid and consistent representations of action sequences for building a bridge between labeled and unlabeled samples in the semi-supervised AQA. To address the issue, we propose a Self-supervised sub-Action Parsing Network (SAP-Net) that employs a teacher-student network structure to learn consistent semantic representations between labeled and unlabeled samples for semi-supervised AQA. We perform actor-centric region detection and generate high-quality pseudo-labels in the teacher branch and assists the student branch in learning discriminative action features. We further design a self-supervised sub-action parsing solution to locate and parse fine-grained sub-action sequences. Then, we present the group contrastive learning with pseudo-labels to capture consistent motion-oriented action features in the two branches. We evaluate our proposed SAP-Net on four public datasets: the MTL-AQA, FineDiving, Rhythmic Gymnastics, and FineFS datasets. The experiment results show that our approach outperforms state-of-the-art semi-supervised methods by a significant margin.
Förderung
- Ministry of Science and Technology of China Foreign Young Talents Program
- Sichuan Science and Technology Program
- National Natural Science Foundation of China
- Science and Technology Innovation Committee of Shenzhen Municipality Foundation
Zitieren
APA
Gedamu, K., Ji, Y., Yang, Y., Shao, J., & Shen, H. T. (2024). Self-Supervised Sub-Action Parsing Network for Semi-Supervised Action Quality Assessment. IEEE Transactions on Image Processing, 33, 6057-6070. https://doi.org/10.1109/tip.2024.3468870
Vancouver
Gedamu K, Ji Y, Yang Y, Shao J, Shen HT. Self-Supervised Sub-Action Parsing Network for Semi-Supervised Action Quality Assessment. IEEE Transactions on Image Processing. 2024;33:6057-6070. doi:10.1109/tip.2024.3468870
BibTeX
@article{Gedamu2024,
author = {Gedamu, Kumie and Ji, Yanli and Yang, Yang and Shao, Jie and Shen, Heng Tao},
title = {Self-Supervised Sub-Action Parsing Network for Semi-Supervised Action Quality Assessment},
journal = {IEEE Transactions on Image Processing},
year = {2024},
volume = {33},
pages = {6057--6070},
doi = {10.1109/tip.2024.3468870}
}
EUVIMED