EUVIMEDEUVIMED entdecken
Crossref

Constructing Stronger and Faster Baselines for Skeleton-Based Action Recognition

Yi-Fan Song, Zhang Zhang, Caifeng Shan, Liang Wang

IEEE Transactions on Pattern Analysis and Machine Intelligence · 01.02.2023 · 45 (2) · 1474-1488

DOI: 10.1109/tpami.2022.3157033 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, erschienen am 01.02.2023. Verfasst von Yi-Fan Song und 3 weiteren Autor:innen. Die Arbeit wurde bisher 501-mal zitiert (Crossref) und nennt 62 Literaturangaben. Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China, Shandong Provincial Key Research and Development Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

One essential problem in skeleton-based action recognition is how to extract discriminative features over all skeleton joints. However, the complexity of the recent State-Of-The-Art (SOTA) models for this task tends to be exceedingly sophisticated and over-parameterized. The low efficiency in model training and inference has increased the validation costs of model architectures in large-scale datasets. To address the above issue, recent advanced separable convolutional layers are embedded into an early fused Multiple Input Branches (MIB) network, constructing an efficient Graph Convolutional Network (GCN) baseline for skeleton-based action recognition. In addition, based on such the baseline, we design a compound scaling strategy to expand the model's width and depth synchronously, and eventually obtain a family of efficient GCN baselines with high accuracies and small amounts of trainable parameters, termed EfficientGCN-Bx, where "x" denotes the scaling coefficient. On two large-scale datasets, i.e., NTU RGB+D 60 and 120, the proposed EfficientGCN-B4 baseline outperforms other SOTA methods, e.g., achieving 92.1% accuracy on the cross-subject benchmark of NTU 60 dataset, while being 5.82× smaller and 5.85× faster than MS-G3D, which is one of the SOTA methods. The source code in PyTorch version and the pretrained models are available at https://github.com/yfsong0709/EfficientGCNv1.

Förderung

  • National Key R&D Program of China
  • National Natural Science Foundation of China
  • Shandong Provincial Key Research and Development Program
  • CAS-AIR

Zitieren

APA

Song, Y. F., Zhang, Z., Shan, C., & Wang, L. (2023). Constructing Stronger and Faster Baselines for Skeleton-Based Action Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(2), 1474-1488. https://doi.org/10.1109/tpami.2022.3157033

Vancouver

Song YF, Zhang Z, Shan C, Wang L. Constructing Stronger and Faster Baselines for Skeleton-Based Action Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(2):1474-1488. doi:10.1109/tpami.2022.3157033

BibTeX
@article{Song2023,
  author = {Song, Yi-Fan and Zhang, Zhang and Shan, Caifeng and Wang, Liang},
  title = {Constructing Stronger and Faster Baselines for Skeleton-Based Action Recognition},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2023},
  volume = {45},
  number = {2},
  pages = {1474--1488},
  doi = {10.1109/tpami.2022.3157033}
}
Kostenlos starten →