Multi-hop graph transformer network for 3D human pose estimation

arXiv:2405.03055v1 Announce Type: new
Abstract: Accurate 3D human pose estimation is a challenging task due to occlusion and depth ambiguity. In this paper, we introduce a multi-hop graph transformer network designed for 2D-to-3D human pose estimation in videos by leveraging the strengths of multi-head self-attention and multi-hop graph convolutional networks with disentangled neighborhoods to capture spatio-temporal dependencies and handle long-range interactions. The proposed network architecture consists of a graph attention block composed of stacked layers of multi-head self-attention and graph …

2d-to-3d abstract arxiv attention convolutional cs.cv graph head human multi-head network networks paper self-attention transformer transformer network type videos