Papers › Enhanced skeleton visualization for view invariant human action recognition
Enhanced skeleton visualization for view invariant human action recognition
Mengyuan Liu, Hong Liu, Chen Chen
Human action recognition based on skeletons has wide applications in human–computer interaction and intelligent surveillance. However, view variations and noisy data bring challenges to this task. What’s more, it remains a problem to effectively represent spatio-temporal skeleton sequences. To solve these problems in one goal, this work presents an enhanced skeleton visualization method for view invariant human action recognition. Our method consists of three stages. First, a sequence-based view invariant transform is developed to eliminate the effect of view variations on spatio-temporal locations of skeleton joints. Second, the transformed skeletons are visualized as a series of color images, which implicitly encode the spatio-temporal information of skeleton joints. Furthermore, visual and motion enhancement methods are applied on color images to enhance their local patterns. Third, a convolutional neural networks-based model is adopted to extract robust and discriminative features from color images. The final action class scores are generated by decision level fusion of deep features. Extensive experiments on four challenging datasets consistently demonstrate the superiority of our method.
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 |
|---|---|---|---|---|---|---|---|
| Skeleton Based Action Recognition | NTU RGB+D | Skeleton Visualization | Accuracy (CS) | 80.0 | #113 of 135 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D | Skeleton Visualization | Accuracy (CV) | 87.2 | #113 of 135 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D | Skeleton Visualization | Ensembled Modalities | 4 | #113 of 135 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D 120 | Skeleton Visualization (Single Stream) | Accuracy (Cross-Setup) | 63.2% | #75 of 83 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D 120 | Skeleton Visualization (Single Stream) | Accuracy (Cross-Subject) | 60.3% | #75 of 83 | Archive leaderboard | report |
| Skeleton Based Action Recognition | UWA3D | ESV (Synthesized + Pre-trained) | Accuracy | 73.8% | #2 of 3 | Archive leaderboard | report |
| Skeleton Based Action Recognition | Varying-view RGB-D Action-Skeleton | SK-CNN | Accuracy (AV I) | 43% | #5 of 7 | Archive leaderboard | report |
| Skeleton Based Action Recognition | Varying-view RGB-D Action-Skeleton | SK-CNN | Accuracy (AV II) | 77% | #5 of 7 | Archive leaderboard | report |
| Skeleton Based Action Recognition | Varying-view RGB-D Action-Skeleton | SK-CNN | Accuracy (CS) | 59% | #5 of 7 | Archive leaderboard | report |
| Skeleton Based Action Recognition | Varying-view RGB-D Action-Skeleton | SK-CNN | Accuracy (CV I) | 26% | #5 of 7 | Archive leaderboard | report |
| Skeleton Based Action Recognition | Varying-view RGB-D Action-Skeleton | SK-CNN | Accuracy (CV II) | 68% | #5 of 7 | 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