EUVIMEDEUVIMED entdecken
Crossref

Human action recognition with transformer based on convolutional features

Chengcheng Shi, Shuxin Liu

Intelligent Decision Technologies · 07.06.2024 · 18 (2) · 881-896

DOI: 10.3233/idt-240159 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Intelligent Decision Technologies, erschienen am 07.06.2024. Verfasst von Chengcheng Shi und 1 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 21 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As one of the key research directions in the field of computer vision, human action recognition has a wide range of practical application values and prospects. In the fields of video surveillance, human-computer interaction, sports analysis, and healthcare, human action recognition technology shows a broad application prospect and potential. However, the diversity and complexity of human actions bring many challenges, such as handling complex actions, distinguishing similar actions, coping with changes in viewing angle, and overcoming occlusion problems. To address the challenges, this paper proposes an innovative framework for human action recognition. The framework combines the latest pose estimation algorithms, pre-trained CNN models, and a Vision Transformer to build an efficient system. The first step involves utilizing the latest pose estimation algorithm to accurately extract human pose information from real RGB image frames. Then, a pre-trained CNN model is used to perform feature extraction on the extracted pose information. Finally, the Vision Transformer model is applied for fusion and classification operations on the extracted features. Experimental validation is conducted on two benchmark datasets, UCF 50 and UCF 101, to demonstrate the effectiveness and efficiency of the proposed framework. The applicability and limitations of the framework in different scenarios are further explored through quantitative and qualitative experiments, providing valuable insights and inspiration for future research.

Zitieren

APA

Shi, C., & Liu, S. (2024). Human action recognition with transformer based on convolutional features. Intelligent Decision Technologies, 18(2), 881-896. https://doi.org/10.3233/idt-240159

Vancouver

Shi C, Liu S. Human action recognition with transformer based on convolutional features. Intelligent Decision Technologies. 2024;18(2):881-896. doi:10.3233/idt-240159

BibTeX
@article{Shi2024,
  author = {Shi, Chengcheng and Liu, Shuxin},
  title = {Human action recognition with transformer based on convolutional features},
  journal = {Intelligent Decision Technologies},
  year = {2024},
  volume = {18},
  number = {2},
  pages = {881--896},
  doi = {10.3233/idt-240159}
}
Kostenlos starten →