---
title: "PoseGTAC: Graph Transformer Encoder-Decoder with Atrous Convolution for 3D Human Pose Estimation"
authors:
  - "Yiran Zhu"
  - "Xing Xu"
  - "Fumin Shen"
  - "Yanli Ji"
  - "Lianli Gao"
  - "Heng Tao Shen"
doi: "10.24963/ijcai.2021/188"
url: "https://ijcai.org/proceedings/2021/188"
pdf: "https://ijcai.org/proceedings/2021/0188.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "1359-1365"
track: "Main Track"
keywords:
  - "Computer Vision: Biometrics, Face and Gesture Recognition"
  - "Humans and AI: Human-Computer Interaction"
  - "Computer Vision: Action Recognition"
---

# PoseGTAC: Graph Transformer Encoder-Decoder with Atrous Convolution for 3D Human Pose Estimation

Yiran Zhu, Xing Xu, Fumin Shen, Yanli Ji, Lianli Gao, Heng Tao Shen

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 1359-1365. DOI: [10.24963/ijcai.2021/188](https://doi.org/10.24963/ijcai.2021/188)

## Abstract

Graph neural networks (GNNs) have been widely used in the 3D human pose estimation task, since the pose representation of a human body can be naturally modeled by the graph structure. Generally, most of the existing GNN-based models utilize the restricted receptive fields of filters and single-scale information, while neglecting the valuable multi-scale contextual information. To tackle this issue, we propose a novel Graph Transformer Encoder-Decoder with Atrous Convolution, named PoseGTAC, to effectively extract multi-scale context and long-range information. In our proposed PoseGTAC model, Graph Atrous Convolution (GAC) and Graph Transformer Layer (GTL), respectively for the extraction of local multi-scale and global long-range information, are combined and stacked in an encoder-decoder structure, where graph pooling and unpooling are adopted for the interaction of multi-scale information from local to global (e.g., part-scale and body-scale). Extensive experiments on the Human3.6M and MPI-INF-3DHP datasets demonstrate that the proposed PoseGTAC model exceeds all previous methods and achieves state-of-the-art performance.