Transcription of Deep High-Resolution Representation Learning for Human ...
{{id}} {{{paragraph}}}
Deep High-Resolution Representation Learning for Human Pose estimation Ke Sun1,2 Bin Xiao2 Dong Liu1 Jingdong Wang2. 1. University of Science and Technology of China 2 Microsoft Research Asia [ ] 25 Feb 2019. Abstract depth In this paper, we are interested in the Human pose es- 1 . timation problem with a focus on Learning reliable high - scale resolution representations. Most existing methods recover 2 . High-Resolution representations from low- resolution repre- sentations produced by a high -to-low resolution network. 4 . Instead, our proposed network maintains High-Resolution feature conv.
Human pose estimation, a.k.a. keypoint detection, aims to detect the locations of Kkeypoints or parts (e.g., elbow, wrist, etc) from an image I of size W H 3. The state-of-the-art methods transform this problem to estimating K heatmaps of size W0 H0, fH 1;H 2;:::;H Kg, where each heatmap H k indicates the location confidence of the kth keypoint.
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document:
{{id}} {{{paragraph}}}