English

DeepPose: Human Pose Estimation via Deep Neural Networks

Computer Vision and Pattern Recognition 2016-11-18 v3

Abstract

We propose a method for human pose estimation based on Deep Neural Networks (DNNs). The pose estimation is formulated as a DNN-based regression problem towards body joints. We present a cascade of such DNN regressors which results in high precision pose estimates. The approach has the advantage of reasoning about pose in a holistic fashion and has a simple but yet powerful formulation which capitalizes on recent advances in Deep Learning. We present a detailed empirical analysis with state-of-art or better performance on four academic benchmarks of diverse real-world images.

Keywords

Cite

@article{arxiv.1312.4659,
  title  = {DeepPose: Human Pose Estimation via Deep Neural Networks},
  author = {Alexander Toshev and Christian Szegedy},
  journal= {arXiv preprint arXiv:1312.4659},
  year   = {2016}
}

Comments

IEEE Conference on Computer Vision and Pattern Recognition, 2014

R2 v1 2026-06-22T02:29:09.205Z