Semantic Scholar Open Access 2017 914 sitasi

Integral Human Pose Regression

Xiao Sun Bin Xiao Shuang Liang Yichen Wei

Abstrak

State-of-the-art human pose estimation methods are based on heat map representation. In spite of the good performance, the representation has a few issues in nature, such as not differentiable and quantization error. This work shows that a simple integral operation relates and unifies the heat map representation and joint regression, thus avoiding the above issues. It is differentiable, efficient, and compatible with any heat map based methods. Its effectiveness is convincingly validated via comprehensive ablation experiments under various settings, specifically on 3D pose estimation, for the first time.

Topik & Kata Kunci

Computer Science

Penulis (4)

Xiao Sun

Bin Xiao

Shuang Liang

Yichen Wei

Format Sitasi

APA MLA BibTeX

Sun, X., Xiao, B., Liang, S., Wei, Y. (2017). Integral Human Pose Regression. https://doi.org/10.1007/978-3-030-01231-1_33

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →

Lihat di Sumber doi.org/10.1007/978-3-030-01231-1_33

Informasi Jurnal

Tahun Terbit: 2017
Bahasa: en
Total Sitasi: 914×
Sumber Database: Semantic Scholar
DOI: 10.1007/978-3-030-01231-1_33
Akses: Open Access ✓