Transcription of HigherHRNet: Scale-Aware Representation Learning for ...
{{id}} {{{paragraph}}}
Example: marketing
HigherHRNet: Scale-Aware Representation Learning for ...
higherhrnet : Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation Bowen Cheng1 , Bin Xiao2 , Jingdong Wang2 , Honghui Shi1,3 , Thomas S. Huang1 , Lei Zhang2. 1. UIUC, 2 Microsoft, 3 University of Oregon Abstract CNN. Heatmap CNN Aggregation Bottom-up human pose estimation methods have diffi- CNN. culties in predicting the correct pose for small persons due to challenges in scale variation. In this paper, we present higherhrnet : a novel bottom-up human pose (a) Image pyramid. estimation method for Learning Scale-Aware representa- tions using high -resolution feature pyramids. Equipped CNN. with multi-resolution supervision for training and multi- resolution aggregation for inference, the proposed ap- (b) Upsampling input. proach is able to solve the scale variation challenge Heatmap HRNet Aggregation in bottom-up multi-person pose estimation and local- ize keypoints more precisely, especially for small person.
scale fusions between branches, HRNet [38, 40] can gener-ate high resolution feature maps with rich semantic. We adopt HRNet [38, 40] as our base network to gener-ate high-quality feature maps. And we add a deconvolution module to generate higher resolution feature maps to pre-dict heatmaps. The resulting model is named “Scale-Aware
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: