3DInAction: Understanding Human Actions in 3D Point Clouds
This addresses the challenge of understanding human actions in 3D point clouds for computer vision applications, representing an incremental advance in a niche area.
The paper tackles the problem of 3D point cloud action recognition, which is under-explored due to data limitations like lack of structure and permutation invariance, and proposes a method that achieves improved performance on datasets such as DFAUST and IKEA ASM.
We propose a novel method for 3D point cloud action recognition. Understanding human actions in RGB videos has been widely studied in recent years, however, its 3D point cloud counterpart remains under-explored. This is mostly due to the inherent limitation of the point cloud data modality -- lack of structure, permutation invariance, and varying number of points -- which makes it difficult to learn a spatio-temporal representation. To address this limitation, we propose the 3DinAction pipeline that first estimates patches moving in time (t-patches) as a key building block, alongside a hierarchical architecture that learns an informative spatio-temporal representation. We show that our method achieves improved performance on existing datasets, including DFAUST and IKEA ASM. Code is publicly available at https://github.com/sitzikbs/3dincaction.