Papers › Action Machine: Rethinking Action Recognition in Trimmed Videos
Action Machine: Rethinking Action Recognition in Trimmed Videos
Jiagang Zhu, Wei Zou, Liang Xu, Yiming Hu, Zheng Zhu, Manyu Chang, Jun-Jie Huang, Guan Huang, Dalong Du
Existing methods in video action recognition mostly do not distinguish human body from the environment and easily overfit the scenes and objects. In this work, we present a conceptually simple, general and high-performance framework for action recognition in trimmed videos, aiming at person-centric modeling. The method, called Action Machine, takes as inputs the videos cropped by person bounding boxes. It extends the Inflated 3D ConvNet (I3D) by adding a branch for human pose estimation and a 2D CNN for pose-based action recognition, being fast to train and test. Action Machine can benefit from the multi-task training of action recognition and pose estimation, the fusion of predictions from RGB images and poses. On NTU RGB-D, Action Machine achieves the state-of-the-art performance with top-1 accuracies of 97.2% and 94.3% on cross-view and cross-subject respectively. Action Machine also achieves competitive performance on another three smaller action recognition datasets: Northwestern UCLA Multiview Action3D, MSR Daily Activity3D and UTD-MHAD. Code will be made available.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Action Recognition | NTU RGB+D | Action Machine (RGB only) | Accuracy (CS) | 94.3 | #11 of 28 | Archive leaderboard | report |
| Action Recognition | NTU RGB+D | Action Machine (RGB only) | Accuracy (CV) | 97.2 | #11 of 28 | Archive leaderboard | report |
| Action Recognition | UTD-MHAD | Action Machine (RGB only) | Accuracy | 92.5 | #1 of 1 | Archive leaderboard | report |
| Multimodal Activity Recognition | MSR Daily Activity3D dataset | Action Machine (RGB only) | Accuracy | 93.0 | #3 of 6 | Archive leaderboard | report |
| Multimodal Activity Recognition | UTD-MHAD | Action Machine | Accuracy (CS) | 92.5 | #4 of 5 | Archive leaderboard | report |
| Skeleton Based Action Recognition | N-UCLA | Action Machine | Accuracy | 92.3% | #22 of 25 | 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