MAGR: Manifold-Aligned Graph Regularization for Continual Action Quality Assessment
arxiv(2024)
摘要
Action Quality Assessment (AQA) evaluates diverse skills but models struggle
with non-stationary data. We propose Continual AQA (CAQA) to refine models
using sparse new data. Feature replay preserves memory without storing raw
inputs. However, the misalignment between static old features and the
dynamically changing feature manifold causes severe catastrophic forgetting. To
address this novel problem, we propose Manifold-Aligned Graph Regularization
(MAGR), which first aligns deviated old features to the current feature
manifold, ensuring representation consistency. It then constructs a graph
jointly arranging old and new features aligned with quality scores. Experiments
show MAGR outperforms recent strong baselines with up to 6.56
and 9.05
split datasets, respectively. This validates MAGR for continual assessment
challenges arising from non-stationary skill variations.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要