YADAV-THESIS-2021.pdf (974.45 kB)
Download file

Primal-Dual Graph Attention Networks for 3D Human Pose Estimation

Download (974.45 kB)
thesis
posted on 01.05.2021, 00:00 by Harsh Yadav
Graph convolution networks (GCNs) have shown good performance in 3D human pose estimation. However, GCNs are limited as they only focus on neighboring nodes for each node and have a fixed graph structure. To address these limitations, we propose a novel architecture called Primal-Dual Graph Attention Network. It consists of two parallel branches – the Primal branch, which applies feature-mask attention along with feature aggregation and attention across body-joints, and the Dual branch, which applies body-joint-mask attention and computes the correlation between feature dimensions. We sum the output of these two branches to get the estimated pose in 3D. This structure helps the network to generate improved feature representations and thus improves model performance. In this research, we use the public Human3.6M dataset.

History

Advisor

Tang, Wei

Chair

Tang, Wei

Department

Computer Science

Degree Grantor

University of Illinois at Chicago

Degree Level

Masters

Degree name

MS, Master of Science

Committee Member

Zhang, Xinhua Caragea, Cornelia

Submitted date

May 2021

Thesis type

application/pdf

Language

en

Usage metrics

Categories

Exports