Research map / Video / Action recognition
Spatio-Temporal Naive-Bayes Nearest-Neighbor (ST-NBNN) for Skeleton-Based Action Recognition
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add learned spatio-temporal bilinear weights to NBNN | NBNN · MSR-Action3D average | accuracy: 91.4 -> 94.8 | Helped |
| Add learned spatio-temporal bilinear weights to NBNN | NBNN · UTKinect | accuracy: 95.5 -> 98.0 | Helped |
| Add learned spatio-temporal bilinear weights to NBNN | NBNN · Berkeley MHAD | accuracy: 88.0 -> 100.0 | Helped |
| Use 15 temporal stages instead of no fixed stage setting (ablation) | NBNN · MSR-Action3D average | accuracy: 91.4 -> 91.7 | Helped |
| Use 15 temporal stages instead of no fixed stage setting (ablation) | NBNN · UTKinect | accuracy: 95.5 -> 95.5 | No clear effect |
| Learn a separate linear-SVM weight for every distance-matrix element (ablation) | NBNN · MSR-Action3D | accuracy: AS1: 85.8 -> 90.6; AS2: 92.0 -> 90.3; AS3: 96.4 -> 96.4 | Mixed |
| Learn a separate linear-SVM weight for every distance-matrix element (ablation) | NBNN · UTKinect | accuracy: 95.5 -> 94.0 | Hurt |
| Learn a separate linear-SVM weight for every distance-matrix element (ablation) | NBNN · Berkeley MHAD | accuracy: 88.0 -> 100.0 | Helped |
| Increase the number of temporal stages beyond 11 (ablation) | ST-NBNN · MSR-Action3D | accuracy | No clear effect |
| Use only 3 poses per stage when the stage count exceeds 11 (ablation) | ST-NBNN · MSR-Action3D | accuracy | Helped |
| Add random coordinate noise to an increasing proportion of joints (ablation) | ST-NBNN · Berkeley MHAD | accuracy | Mixed |
| Constrain temporal weights to be nonnegative and sum to the stage count (ablation) | ST-NBNN · 3D action recognition | accuracy | Helped |
Closest papers by meaning
- Towards To-a-T Spatio-Temporal Focus for Skeleton-Based Action Recognition (AAAI 2022 · similarity 0.90)
- Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition (AAAI 2018 · similarity 0.88)
- Spatio-Temporal Graph Routing for Skeleton-Based Action Recognition (AAAI 2019 · similarity 0.88)
- A New Representation of Skeleton Sequences for 3D Action Recognition (CVPR 2017 · similarity 0.88)
- Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition (CVPR 2025 · similarity 0.88)
- Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition (CVPR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.