Cargando…

HPnet: Hybrid Parallel Network for Human Pose Estimation

Hybrid models which combine the convolution and transformer model achieve impressive performance on human pose estimation. However, the existing hybrid models on human pose estimation, which typically stack self-attention modules after convolution, are prone to mutual conflict. The mutual conflict e...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Haoran, Yao, Hongxun, Hou, Yuxin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10181615/
https://www.ncbi.nlm.nih.gov/pubmed/37177628
http://dx.doi.org/10.3390/s23094425