papers AI Learner
The Github is limit! Click to go to the new site.

Spatial Shortcut Network for Human Pose Estimation

2019-04-05
Te Qi (1), Bayram Bayramli (1), Usman Ali (1), Qinchuan Zhang (1), Hongtao Lu (1) ((1) Shanghai Jiao Tong University)

Abstract

Like many computer vision problems, human pose estimation is a challenging problem in that recognizing a body part requires not only information from local area but also from areas with large spatial distance. In order to spatially pass information, large convolutional kernels and deep layers have been normally used, introducing high computation cost and large parameter space. Luckily for pose estimation, human body is geometrically structured in images, enabling modeling of spatial dependency. In this paper, we propose a spatial shortcut network for pose estimation task, where information is easier to flow spatially. We evaluate our model with detailed analyses and present its outstanding performance with smaller structure.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1904.03141

PDF

https://arxiv.org/pdf/1904.03141


Similar Posts

Comments