Research map / Continual learning / Class-incremental
MAGR: Manifold-Aligned Graph Regularization for Continual Action Quality Assessment
Kanglei Zhou, Liyuan Wang, Xingxing Zhang, Hubert P. H. Shum, Frederick W. B. Li, Jianguo Li, Xiaohui Liang
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 manifold projector to align old features to current manifold (ablation) | MAGR · MTL-AQA | rho_avg: 0.6949 -> 0.8979 | Improved |
| add residual link in the manifold projector (ablation) | MAGR · MTL-AQA | rho_avg: 0.8391 -> 0.8979 | Improved |
| add intra-inter-joint graph regularizer (ablation) | MAGR · MTL-AQA | rho_avg: 0.7362 -> 0.8979 | Improved |
| add joint (global) graph regularizer on top of intra-inter (ablation) | MAGR · MTL-AQA | rho_avg: 0.7839 -> 0.8979 | Improved |
| use KL divergence instead of MSE in graph regularization (ablation) | MAGR · MTL-AQA | rho_avg: 0.8447 -> 0.8979 | Improved |
| use ordered uniform sampling instead of random sampling for the memory bank (ablation) | MAGR · MTL-AQA | rho_aft: 0.0876 -> 0.0223 | Improved |
| use feature replay with updated backbone instead of raw data replay (Feature MER vs MER) | MER · MTL-AQA | rho_avg: 0.8720 -> 0.7283 | Hurt |
| reduce memory to 3 features per session | MAGR · MTL-AQA | rho_avg | Hurt |
| increase feature replay memory from 5 to 11 samples per session | MAGR · MTL-AQA | rho_avg | No clear effect |
| use MAGR vs strongest baseline on larger feature deviation datasets | MAGR · FineDiving, MTL-AQA, UNLV-Dive | overall correlation gain (%): 5.66, 6.56, 15.64 at MSE deviations 26.85, 35.28, 51.75 | Improved |
| sequential fine-tuning without memory | baseline · MTL-AQA | rho_avg: 0.9360 -> 0.5458 | Hurt |
Later papers that compared with this method
1 later accepted paper reports MAGR as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization (TPAMI 2026 · better on 8 of 8 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization (TPAMI 2026 · similarity 0.96)
- BriMA: Bridged Modality Adaptation for Multi-Modal Continual Action Quality Assessment (CVPR 2026 · similarity 0.87)
- LucidAction: A Hierarchical and Multi-model Dataset for Comprehensive Action Quality Assessment (NeurIPS 2024 · similarity 0.85)
- FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment (CVPR 2024 · similarity 0.84)
- Measuring Representational Shifts in Continual Learning: A Linear Transformation Perspective (ICML 2025 · similarity 0.83)
- Quantifying Uncertainty in Error Consistency: Towards Reliable Behavioral Comparison of Classifiers (NeurIPS 2025 · similarity 0.83)
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.
