GeometryMotion-Transformer: An End-to-End Framework for 3D Action Recognition
Jiaheng Liu, Jinyang Guo, Dong Xu
Abstract
In this work, we propose a new end-to-end optimized two-stream framework called GeometryMotion-Transformer (GMT) for 3D action recognition. We first observe that the existing 3D action recognition approaches cannot well extract motion representations from point cloud sequences. Specifically, when extracting motion representations, the existing approaches do not explicitly consider one-to-one correspondence among frames. Besides, the existing methods only extract the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">single-scale</i> motion representations, which cannot well model the complex motion patterns of moving objects in point cloud sequences. To address these issues, we first propose the feature extraction module (FEM) to generate one-to-one correspondence among frames without using the voxelization process, and explicitly extract both geometry and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">multi-scale</i> motion representations from raw point clouds. Moreover, we also observe the existing two-stream 3D action recognition approaches simply concatenate or add the geometry and motion features, which cannot well exploit the relationship between two-steam features. To this end, we also propose an improved transformer-based feature fusion module (FFM) to effectively fuse the two-stream features. Based on the proposed FEM and FFM, we build our GMT for 3D action recognition. Extensive experimental results on four benchmark datasets demonstrate the effectiveness of our backbone GMT.