Adaptive graphical model network for 2D handpose estimation

Kong，Deying1; Chen，Yifei2; Ma，Haoyu3; Yan，Xiangyi4; Xie，Xiaohui1

2020

30th British Machine Vision Conference 2019, BMVC 2019

In this paper, we propose a new architecture called Adaptive Graphical Model Network (AGMN) to tackle the task of 2D hand pose estimation from a monocular RGB image. The AGMN consists of two branches of deep convolutional neural networks for calculating unary and pairwise potential functions, followed by a graphical model inference module for integrating unary and pairwise potentials. Unlike existing architectures proposed to combine DCNNs with graphical models, our AGMN is novel in that the parameters of its graphical model are conditioned on and fully adaptive to individual input images. Experiments show that our approach outperforms the state-of-the-art method used in 2D hand keypoints estimation by a notable margin on two public datasets.

Others

English

2-s2.0-85085507108

Scopus

1.University of California,Irvine,United States
2.Tencent,
3.Southeast University,
4.Southern University of Science and Technology,

Kong，Deying,Chen，Yifei,Ma，Haoyu,et al. Adaptive graphical model network for 2D handpose estimation[C],2020.