Make Skeleton-based Action Recognition Model Smaller, Faster and Better

07/23/2019
by   Fan Yang, et al.
0

Although skeleton-based action recognition has achieved great success in recent years, most of the existing methods may suffer from a large model size and slow execution speed. To alleviate this issue, we analyze skeleton sequence properties to propose a Double-feature Double-motion Network (DD-Net) for skeleton-based action recognition. By using a lightweight network structure (i.e., 0.15 million parameters), DD-Net can reach a super fast speed, as 3,500 FPS on one GPU, or, 2,000 FPS on one CPU. By employing robust features, DD-Net achieves the state-of-the-art performance on our experiment datasets: SHREC (i.e., hand actions) and JHMDB (i.e., body actions). Our code will be released with this paper later.

READ FULL TEXT

page 1

page 2

research
03/17/2020

Predictively Encoded Graph Convolutional Network for Noise-Robust Skeleton-based Action Recognition

In skeleton-based action recognition, graph convolutional networks (GCNs...
research
01/27/2021

NTU60-X: Towards Skeleton-based Recognition of Subtle Human Actions

The lack of fine-grained joints such as hand fingers is a fundamental pe...
research
08/06/2022

AFE-CNN: 3D Skeleton-based Action Recognition with Action Feature Enhancement

Existing 3D skeleton-based action recognition approaches reach impressiv...
research
03/22/2021

AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition

Existing methods for skeleton-based action recognition mainly focus on i...
research
05/19/2022

PYSKL: Towards Good Practices for Skeleton Action Recognition

We present PYSKL: an open-source toolbox for skeleton-based action recog...
research
03/31/2022

SpatioTemporal Focus for Skeleton-based Action Recognition

Graph convolutional networks (GCNs) are widely adopted in skeleton-based...
research
07/07/2020

Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action Recognition

Dynamic skeletal data, represented as the 2D/3D coordinates of human joi...

Please sign up or login with your details

Forgot password? Click here to reset