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

arXiv 2019  ·  Fan Yang, Sakriani Sakti, Yang Wu, Satoshi Nakamura ·

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 experimental datasets: SHREC (i.e., hand actions) and JHMDB (i.e., body actions). Our code will be released with this paper later.

PDF Abstract

Datasets

JHMDB SHREC

Results from the Paper
Edit

 Ranked #1 on Hand Gesture Recognition on DHG-14

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Hand Gesture Recognition DHG-14 DD-Net Accuracy 94.6 # 1
Compare
Hand Gesture Recognition DHG-28 DD-Net Accuracy 91.9 # 1
Compare
Skeleton Based Action Recognition J-HMDB DD-Net Accuracy (RGB+pose) - # 11
Compare
Accuracy (pose) 77.2 # 1
Compare
Skeleton Based Action Recognition JHMDB (2D poses only) DD-Net Accuracy 78.0 (average of 3 split train/test) # 1
Compare
Average accuracy of 3 splits 77.2 # 1
Compare
No. parameters 1.82 M # 1
Compare
Hand Gesture Recognition SHREC 2017 track on 3D Hand Gesture Recognition DD-Net 14 gestures accuracy 94.6 # 3
Compare

Methods
Add Remove

No methods listed for this paper. Add relevant methods here
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy