Pattern Recognition
Pattern Recognition
复制标题
DOI：
10.1002/047134608x.w5513.pub2
复制
发表时间：
2019-02
期刊：
影响因子：
--
通讯作者：
K. Kulkarni;P. Turaga;Anuj Srivastava;Rama Chellappa
中科院分区：
文献类型：
--
作者：
K. Kulkarni;P. Turaga;Anuj Srivastava;Rama Chellappa
细粒度动作识别涉及对人与特定物体之间微妙的相互作用所组成的可变长度大小的类似动作进行比较。因此，我们提出了一种基于动态核的方法来处理变长模式，以有效识别细粒度动作。首先，我们提取每个视频的局部时空特征，以有效捕获外观和运动信息。在提取的所有细粒度动作特征上训练一个与动作无关的高斯混合模型（AIGMM）来分析时空信息，并保持细粒度动作之间的局部相似性。然后，利用AIGMM的统计量，即均值、协方差和后验，将统计量映射到核特征空间，构建核，寻找任意两个细粒度动作之间的相似性。在MERL、JIGSAWS、KSCGR和MPII cooking2四种细粒度动作数据集上，我们使用GMM平均区间核、超向量核、中间匹配核等三种动态核证明了所提出方法的有效性
Fine-grained action recognition involves comparison of similar actions of variable-length size consisting of subtle interactions between human and specific objects. Hence, we propose a dynamic kernel-based approach to handle the variable-length patterns for effective recognition of fine-grained actions. Initially, we extract local spatio-temporal features for each video to capture appearance and motion information effectively. An action-independent Gaussian mixture model (AIGMM) is trained on the extracted features of all fine-grained actions to analyze spatio-temporal information and preserve the local similarities among fine-grained actions. Then, the statistics of AIGMM, namely, mean, covariance, and posteriors are used to build the kernels for finding the similarity between any two fine-grained actions by mapping statistics to kernel feature space. We demonstrate the effectiveness of proposed approach using three dynamic kernels i.e., GMM mean interval kernel, supervector kernel, intermediate matching kernel on four varieties of fine-grained action datasets, namely, MERL, JIGSAWS, KSCGR, and MPII cooking2