Research map / Video / Action recognition
SPAR: A Sequential Primacy and Attribution Ranking Framework for Skill Determination
Hui Yu, Xiao Ke, Zhihong Zeng, Huangbiao Xu, Huanqi Wu, Yaru Su
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 SaCM to the LSTM reference (ablation) | LSTM reference · BEST | avg accuracy: 72.25 -> 78.37 | Improved |
| add SaCM to the LSTM reference (ablation) | LSTM reference · LOGO | Spearman rho: 0.474 -> 0.604 | Improved |
| add SaCM to the LSTM reference (ablation) | LSTM reference · LOGO | R-l2: 21.146 -> 11.479 | Improved |
| add TWW (without JBM) on top of SaCM (ablation) | SPAR · BEST | avg accuracy: 78.37 -> 83.49 | Improved |
| add TWW (without JBM) on top of SaCM (ablation) | SPAR · LOGO | Spearman rho: 0.604 -> 0.652 | Improved |
| add TWW (without JBM) on top of SaCM (ablation) | SPAR · LOGO | R-l2: 11.479 -> 5.969 | Improved |
| add JBM loss on top of SaCM and TWW (ablation) | SPAR · BEST | avg accuracy: 83.49 -> 88.56 | Improved |
| add JBM loss on top of SaCM and TWW (ablation) | SPAR · LOGO | Spearman rho: 0.652 -> 0.749 | Improved |
| add JBM loss on top of SaCM and TWW (ablation) | SPAR · LOGO | R-l2: 5.969 -> 3.743 | Improved |
| use SaCM instead of attention module (also w/o JBM) (ablation) | SPAR · BEST | avg accuracy: 75.92 -> 88.56 | Improved |
| use SaCM instead of attention module (also w/o JBM) (ablation) | SPAR · LOGO | Spearman rho: 0.544 -> 0.749 | Improved |
| include TWW (ablation) | SPAR · BEST | avg accuracy: 80.38 -> 88.56 | Improved |
Closest papers by meaning
- The Pros and Cons: Rank-Aware Temporal Attention for Skill Determination in Long Videos (CVPR 2019 · similarity 0.89)
- SkillSpotter: Pose-Aware Multi-View Skilled Action Detection and Grading in Ego-Exo Videos (ECCV 2026 · similarity 0.86)
- Learning Skill-Attributes for Transferable Assessment in Video (NeurIPS 2025 · similarity 0.85)
- SLVMBench: Skill Learning from Video Memory (NeurIPS 2026 · similarity 0.84)
- FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment (CVPR 2024 · similarity 0.84)
- ExAct: A Video-Language Benchmark for Expert Action Analysis (NeurIPS 2025 · similarity 0.84)
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.
