Make Skeleton-based Action Recognition Model Smaller, Faster and Better
This work addresses efficiency issues for researchers and practitioners in action recognition, offering a lightweight and fast model, though it is incremental as it builds on existing methods.
The paper tackles the problem of large model size and slow speed in skeleton-based action recognition by proposing DD-Net, which achieves state-of-the-art performance on SHREC and JHMDB datasets with 0.15 million parameters and speeds up to 3,500 FPS on GPU.
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.