Clustering-aware structure-constrained low-rank representation model for learning human action attributes
Clustering-aware structure-constrained low-rank representation model for learning human action attributes
复制标题
DOI：
10.1109/ivmspw.2016.7528184
复制
发表时间：
2016-07
期刊：
影响因子：
--
通讯作者：
Tong Wu;Prudhvi K. Gurram;R. Rao;W. Bajwa
中科院分区：
文献类型：
--
作者：
Tong Wu;Prudhvi K. Gurram;R. Rao;W. Bajwa
提出了一种基于子空间联合（union-of-subspaces，UoS）模型从高维视频序列中学习有意义的人体动作属性的方法。该模型假设每个动作属性由一个子空间表示。它提出了一种扩展现有的低秩表示（LRR），称为聚类感知结构约束的低秩表示（CS-LRR）模型，用于人类动作属性的无监督学习。建议CS-LRR模型克服了现有技术的缺点，它能够处理不相交的子空间，并通过执行最佳谱聚类的子空间。提出了一种有效的线性交替方向法（LADM）来求解CS-LRR优化问题。人类动作或活动被表示为从一个动作属性到另一个动作属性的转换序列，并且可以由子空间转换向量唯一地表示。这些子空间转移向量用于人体动作识别。通过在两个真实世界的动作识别数据集上的实验，证明了该模型的有效性。
This paper addresses the problem of learning meaningful human action attributes from high-dimensional video sequences based on union-of-subspaces (UoS) model. The model hypothesizes that each action attribute is represented by a subspace. It puts forth an extension of existing low-rank representation (LRR), termed the clustering-aware structure-constrained low-rank representation (CS-LRR) model, for unsupervised learning of human action attributes. The proposed CS-LRR model overcomes the shortcomings of existing techniques by its ability to handle disjoint subspaces, and by performing optimal spectral clustering of the subspaces. An efficient linear alternating direction method (LADM) is developed to solve the CS-LRR optimization problem. A human action or activity is represented as a sequence of transitions from one action attribute to another and can be uniquely represented by a subspace transition vector. These subspace transition vectors are used for human action recognition. The effectiveness of the proposed model is demonstrated through experiments on two real-world datasets for action recognition.