DeepAI AI Chat
Log In Sign Up

3DV: 3D Dynamic Voxel for Action Recognition in Depth Video

by   Yancheng Wang, et al.
Megvii Technology Limited
Huazhong University of Science u0026 Technology
Agency for Science, Technology and Research
University at Buffalo

To facilitate depth-based 3D action recognition, 3D dynamic voxel (3DV) is proposed as a novel 3D motion representation. With 3D space voxelization, the key idea of 3DV is to encode 3D motion information within depth video into a regular voxel set (i.e., 3DV) compactly, via temporal rank pooling. Each available 3DV voxel intrinsically involves 3D spatial and motion feature jointly. 3DV is then abstracted as a point set and input into PointNet++ for 3D action recognition, in the end-to-end learning way. The intuition for transferring 3DV into the point set form is that, PointNet++ is lightweight and effective for deep feature learning towards point set. Since 3DV may lose appearance clue, a multi-stream 3D action recognition manner is also proposed to learn motion and appearance feature jointly. To extract richer temporal order information of actions, we also divide the depth video into temporal splits and encode this procedure in 3DV integrally. The extensive experiments on 4 well-established benchmark datasets demonstrate the superiority of our proposition. Impressively, we acquire the accuracy of 82.4 RGB+D 120 [13] with the cross-subject and crosssetup test setting respectively. 3DV's code is available at


page 2

page 4


Dynamic Appearance: A Video Representation for Action Recognition with Joint Training

Static appearance of video may impede the ability of a deep neural netwo...

Is Appearance Free Action Recognition Possible?

Intuition might suggest that motion and dynamic information are key to v...

A Dynamic Multi-Scale Voxel Flow Network for Video Prediction

The performance of video prediction has been greatly boosted by advanced...

Human Action Recognition Based on Multi-scale Feature Maps from Depth Video Sequences

Human action recognition is an active research area in computer vision. ...

LIGAR: Lightweight General-purpose Action Recognition

Growing amount of different practical tasks in a video understanding pro...

Memory-Augmented Temporal Dynamic Learning for Action Recognition

Human actions captured in video sequences contain two crucial factors fo...

Action Recognition Using Volumetric Motion Representations

Traditional action recognition models are constructed around the paradig...

Code Repositories


Action Recognition CVPR2020

view repo


3D Vision project: 3D video action recognition

view repo