EUVIMEDEUVIMED entdecken
Crossref

SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation

Xiaoqi An, Lin Zhao, Chen Gong, Nannan Wang, Di Wang, Jian Yang

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (2) · 691-699

DOI: 10.1609/aaai.v38i2.27826 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Xiaoqi An und 5 weiteren Autor:innen. Die Arbeit wurde bisher 39-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-resolution representation is essential for achieving good performance in human pose estimation models. To obtain such features, existing works utilize high-resolution input images or fine-grained image tokens. However, this dense high-resolution representation brings a significant computational burden. In this paper, we address the following question: "Only sparse human keypoint locations are detected for human pose estimation, is it really necessary to describe the whole image in a dense, high-resolution manner?" Based on dynamic transformer models, we propose a framework that only uses Sparse High-resolution Representations for human Pose estimation (SHaRPose). In detail, SHaRPose consists of two stages. At the coarse stage, the relations between image regions and keypoints are dynamically mined while a coarse estimation is generated. Then, a quality predictor is applied to decide whether the coarse estimation results should be refined. At the fine stage, SHaRPose builds sparse high-resolution representations only on the regions related to the keypoints and provides refined high-precision human pose estimations. Extensive experiments demonstrate the outstanding performance of the proposed method. Specifically, compared to the state-of-the-art method ViTPose, our model SHaRPose-Base achieves 77.4 AP (+0.5 AP) on the COCO validation set and 76.7 AP (+0.5 AP) on the COCO test-dev set, and infers at a speed of 1.4x faster than ViTPose-Base. Code is available at https://github.com/AnxQ/sharpose.

Zitieren

APA

An, X., Zhao, L., Gong, C., Wang, N., Wang, D., & Yang, J. (2024). SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation. Proceedings of the AAAI Conference on Artificial Intelligence, 38(2), 691-699. https://doi.org/10.1609/aaai.v38i2.27826

Vancouver

An X, Zhao L, Gong C, Wang N, Wang D, Yang J. SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(2):691-699. doi:10.1609/aaai.v38i2.27826

BibTeX
@article{An2024,
  author = {An, Xiaoqi and Zhao, Lin and Gong, Chen and Wang, Nannan and Wang, Di and Yang, Jian},
  title = {SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {2},
  pages = {691--699},
  doi = {10.1609/aaai.v38i2.27826}
}
Kostenlos starten →