Research map / Video / Action recognition
Action Assessment by Joint Relation Graphs
Jia-Hui Pan, Jibin Gao, Wei-Shi Zheng
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 Joint Commonality Module (ablation) | full model · AQA-7 Olympic actions (average) | Spearman correlation: 0.7423 -> 0.7849 | Improved |
| add Joint Difference Module (ablation) | full model · AQA-7 Olympic actions (average) | Spearman correlation: 0.7455 -> 0.7849 | Improved |
| add Joint Difference Module (ablation) | full model · AQA-7 Skiing | Spearman correlation: 0.6191 -> 0.6006 | Hurt |
| add spatial relation graph (ablation) | full model · AQA-7 Olympic actions (average) | Spearman correlation: 0.7229 -> 0.7849 | Improved |
| add temporal relation graph (ablation) | full model · AQA-7 Olympic actions (average) | Spearman correlation: 0.7423 -> 0.7849 | Improved |
| add feature pooling layer (ablation) | full model · AQA-7 Olympic actions (average) | Spearman correlation: 0.7451 -> 0.7849 | Improved |
| add feature encoders (ablation) | full model · AQA-7 Olympic actions (average) | Spearman correlation: 0.6512 -> 0.7849 | Improved |
| add joint relation graph modeling to whole-scene I3D features (ablation) | whole-scene baseline · AQA-7 Olympic actions (average) | Spearman correlation: 0.7226 -> 0.7849 | Improved |
| add local-patch joint features with mean pooling to whole-scene features | whole-scene baseline · AQA-7 Olympic actions (average) | Spearman correlation: 0.7226 -> 0.7229 | No clear effect |
| switch pose estimator from Mask-RCNN to AlphaPose (ablation) | Ours · AQA-7 Diving | Spearman correlation: 0.7630 -> 0.7558 | No clear effect |
| apply graph model to surgical videos instead of whole+joint baseline | Ours · JIGSAWS average | Spearman correlation: 0.46 -> 0.57 | Improved |
Closest papers by meaning
- Adaptive Action Assessment (TPAMI 2021 · similarity 0.88)
- SportsCap: Monocular 3D Human Motion Capture and Fine-Grained Understanding in Challenging Sports Videos (IJCV 2021 · similarity 0.86)
- Motion Prediction Using Trajectory Cues (ICCV 2021 · similarity 0.86)
- SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition (ECCV 2024 · similarity 0.86)
- Spatio-Temporal Fusion for Human Action Recognition via Joint Trajectory Graph (AAAI 2024 · similarity 0.85)
- Learning Skill-Attributes for Transferable Assessment in Video (NeurIPS 2025 · similarity 0.85)
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.
