Papers
arxiv:2303.06346

3DInAction: Understanding Human Actions in 3D Point Clouds

Published on Mar 29, 2024
Authors:
,
,

Abstract

A hierarchical pipeline estimates time-moving patches to learn spatio-temporal representations for 3D point cloud action recognition, improving results on 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.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2303.06346
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2303.06346 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2303.06346 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2303.06346 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.