建模骨骼关节间非线性关系，提升动作识别准确率
Skeleton-based Action Recognition with Non-linear Dependency Modeling and Hilbert-Schmidt Independence Criterion
- 全连接关节依赖建模，突破物理距离限制
- 在三个数据集上达到最新最高精度
- 无需降维即可区分动作类别，适合高维动作数据
基于骨骼的动作识别是人工智能的重要方向。现有先进方法通常仅关注相邻关节间的依赖关系，难以捕捉远距离关节的非线性关联。此外，多数方法通过估计运动表示的概率密度来区分动作类别，但人体动作的高维特性使此类度量面临固有挑战。本文从两方面解决这些问题：(1) 提出一种新型依赖关系优化方法，显式建模任意关节对之间的依赖关系，有效突破关节距离的限制；(2) 构建一种利用希尔伯特-施密特独立性准则（Hilbert-Schmidt Independence Criterion）区分动作类别的框架，不依赖数据维度，并数学推导出保证精确识别的学习目标。实验表明，该方法在 NTU RGB+D、NTU RGB+D 120 与 Northwestern-UCLA 数据集上均达到当前最优性能。
原文摘要 · Abstract (English)
Human skeleton-based action recognition has long been an indispensable aspect of artificial intelligence. Current state-of-the-art methods tend to consider only the dependencies between connected skeletal joints, limiting their ability to capture non-linear dependencies between physically distant joints. Moreover, most existing approaches distinguish action classes by estimating the probability density of motion representations, yet the high-dimensional nature of human motions invokes inherent difficulties in accomplishing such measurements. In this paper, we seek to tackle these challenges from two directions: (1) We propose a novel dependency refinement approach that explicitly models dependencies between any pair of joints, effectively transcending the limitations imposed by joint distance. (2) We further propose a framework that utilizes the Hilbert-Schmidt Independence Criterion to differentiate action classes without being affected by data dimensionality, and mathematically derive learning objectives guaranteeing precise recognition. Empirically, our approach sets the state-of-the-art performance on NTU RGB+D, NTU RGB+D 120, and Northwestern-UCLA datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。