Papers › Hierarchical Action Classification with Network Pruning
Hierarchical Action Classification with Network Pruning
Mahdi Davoodikakhki, KangKang Yin
Research on human action classification has made significant progresses in the past few years. Most deep learning methods focus on improving performance by adding more network components. We propose, however, to better utilize auxiliary mechanisms, including hierarchical classification, network pruning, and skeleton-based preprocessing, to boost the model robustness and performance. We test the effectiveness of our method on four commonly used testing datasets: NTU RGB+D 60, NTU RGB+D 120, Northwestern-UCLA Multiview Action 3D, and UTD Multimodal Human Action Dataset. Our experiments show that our method can achieve either comparable or better performance on all four datasets. In particular, our method sets up a new baseline for NTU 120, the largest dataset among the four. We also analyze our method with extensive comparisons and ablation studies.
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 | Hierarchical Action Classification (RGB + Pose) | Accuracy (CS) | 95.66 | #7 of 28 | Archive leaderboard | report |
| Action Recognition | NTU RGB+D | Hierarchical Action Classification (RGB + Pose) | Accuracy (CV) | 98.79 | #7 of 28 | Archive leaderboard | report |
| Skeleton Based Action Recognition | N-UCLA | Hierarchical Action Classification (RGB + Pose) | Accuracy | 93.99 | #17 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