Single/multi-view human action recognition via regularized multi-task learning
Single/multi-view human action recognition via regularized multi-task learning
复制标题
DOI：
10.1016/j.neucom.2014.04.090
复制
发表时间：
2015-03
期刊：
影响因子：
6
通讯作者：
Anan Liu;Ning Xu;Yuting Su;Hong Lin;Tong Hao;Zhaoxuan Yang
中科院分区：
文献类型：
--
作者：
Anan Liu;Ning Xu;Yuting Su;Hong Lin;Tong Hao;Zhaoxuan Yang
提出了一种基于正则化多任务学习的单/多视角人体动作识别方法。首先，我们提出了金字塔部分词袋（PPBoW）表示隐式编码的本地视觉特征和人体结构。此外，我们制定的单/多视图人体动作识别的任务到一个部分诱导的多任务学习问题惩罚的图结构和稀疏性，以发现多个视图和身体部位之间的潜在相关性，从而提高性能。实验表明，该方法比标准BoW+SVM方法性能有显著提高。此外，所提出的方法可以实现竞争性能简单地与低维PPBoW表示对国家的最先进的人类动作识别方法KTH和MV-TJU，一个新的多视图动作数据集与RGB，深度和骨架数据由我们的小组准备。
This paper proposes a unified single/multi-view human action recognition method via regularized multi-task learning. First, we propose the pyramid partwise bag of words (PPBoW) representation which implicitly encodes both local visual characteristics and human body structure. Furthermore, we formulate the task of single/multi-view human action recognition into a part-induced multi-task learning problem penalized by graph structure and sparsity to discover the latent correlation among multiple views and body parts and consequently boost the performances. The experiment shows that this method can significantly improve performance over the standard BoW+SVM method. Moreover, the proposed method can achieve competing performance simply with low dimensional PPBoW representation against the state-of-the-art methods for human action recognition on KTH and MV-TJU, a new multi-view action dataset with RGB, depth and skeleton data prepared by our group.