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

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

23 Jul 2019arXiv 2019 7arXiv:1907.09658archive 2025-07-28

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.

PaperPDFCode

Code

fandulu/DD-Net officialmentioned in papermentioned on GitHubtf report
paty0504/SIGNTEGRATE mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action RecognitionHand Gesture RecognitionSkeleton Based Action Recognition

2 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Hand Gesture Recognition DHG-14 DD-Net Accuracy 94.6 #3 of 13 Archive leaderboard report
Hand Gesture Recognition DHG-28 DD-Net Accuracy 91.9 #3 of 9 Archive leaderboard report
Hand Gesture Recognition SHREC 2017 track on 3D Hand Gesture Recognition DD-Net 14 gestures accuracy 94.6 #3 of 3 Archive leaderboard report
Skeleton Based Action Recognition J-HMDB DD-Net Accuracy (RGB+pose) - #12 of 13 Archive leaderboard report
Skeleton Based Action Recognition J-HMDB DD-Net Accuracy (pose) 77.2 #12 of 13 Archive leaderboard report
Skeleton Based Action Recognition JHMDB (2D poses only) DD-Net Accuracy 78.0 (average of 3 split train/test) #2 of 6 Archive leaderboard report
Skeleton Based Action Recognition JHMDB (2D poses only) DD-Net Average accuracy of 3 splits 77.2 #2 of 6 Archive leaderboard report
Skeleton Based Action Recognition JHMDB (2D poses only) DD-Net No. parameters 1.82 M #2 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections