EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Lightweight Context-Aware Feature Transformer Network for Human Pose Estimation

Yanli Ma, Qingxuan Shi, Fan Zhang

Electronics · 09.02.2024 · 13 (4) · 716

DOI: 10.3390/electronics13040716 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 09.02.2024. Verfasst von Yanli Ma und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Natural Science Foundation of Hebei Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We propose a Context-aware Feature Transformer Network (CaFTNet), a novel network for human pose estimation. To address the issue of limited modeling of global dependencies in convolutional neural networks, we design the Transformerneck to strengthen the expressive power of features. Transformerneck directly substitutes 3×3 convolution in the bottleneck of HRNet with a Contextual Transformer (CoT) block while reducing the complexity of the network. Specifically, the CoT first produces keys with static contextual information through 3×3 convolution. Then, relying on query and contextualization keys, dynamic contexts are generated through two concatenated 1×1 convolutions. Static and dynamic contexts are eventually fused as an output. Additionally, for multi-scale networks, in order to further refine the features of the fusion output, we propose an Attention Feature Aggregation Module (AFAM). Technically, given an intermediate input, the AFAM successively deduces attention maps along the channel and spatial dimensions. Then, an adaptive refinement module (ARM) is exploited to activate the obtained attention maps. Finally, the input undergoes adaptive feature refinement through multiplication with the activated attention maps. Through the above procedures, our lightweight network provides powerful clues for the detection of keypoints. Experiments are performed on the COCO and MPII datasets. The model achieves a 76.2 AP on the COCO val2017 dataset. Compared to other methods with a CNN as the backbone, CaFTNet has a 72.9% reduced number of parameters. On the MPII dataset, our method uses only 60.7% of the number of parameters, acquiring similar results to other methods with a CNN as the backbone.

Förderung

  • The Natural Science Foundation of Hebei Province

Zitieren

APA

Ma, Y., Shi, Q., & Zhang, F. (2024). A Lightweight Context-Aware Feature Transformer Network for Human Pose Estimation. Electronics, 13(4), 716. https://doi.org/10.3390/electronics13040716

Vancouver

Ma Y, Shi Q, Zhang F. A Lightweight Context-Aware Feature Transformer Network for Human Pose Estimation. Electronics. 2024;13(4):716. doi:10.3390/electronics13040716

BibTeX
@article{Ma2024,
  author = {Ma, Yanli and Shi, Qingxuan and Zhang, Fan},
  title = {A Lightweight Context-Aware Feature Transformer Network for Human Pose Estimation},
  journal = {Electronics},
  year = {2024},
  volume = {13},
  number = {4},
  pages = {716},
  doi = {10.3390/electronics13040716}
}
Kostenlos starten →