A Hierarchical Model of Shape and Appearance for Human Action Classification
A Hierarchical Model of Shape and Appearance for Human Action Classification
复制标题
DOI：
10.1109/cvpr.2007.383132
复制
发表时间：
2007-06
期刊：
影响因子：
--
通讯作者：
Juan Carlos Niebles;Li Fei-Fei-Li-Fei-Fei-48004138
中科院分区：
文献类型：
--
作者：
Juan Carlos Niebles;Li Fei-Fei-Li-Fei-Fei-48004138
我们提出了一个新的模型，人类行为分类。通过提取静态和动态兴趣点，将视频序列表示为空间和时空特征的集合。我们提出了一个分层模型，可以被描述为一个星座的袋的功能，并能够联合收割机结合空间和时空特征。给定一个新的视频序列，该模型能够在逐帧的基础上对人类动作进行分类。我们在公开的人类行为数据集上测试了该模型[2]，并表明我们的新方法在分类任务上表现良好。我们还进行了对照实验，以表明使用所提出的混合分层模型提高了分类性能的袋特征模型。另外一个实验表明，与使用单一特征类型相比，使用动态和静态特征提供了更丰富的人类行为表示，正如我们在分类任务中的评估所证明的那样。
We present a novel model for human action categorization. A video sequence is represented as a collection of spatial and spatial-temporal features by extracting static and dynamic interest points. We propose a hierarchical model that can be characterized as a constellation of bags-of-features and that is able to combine both spatial and spatial-temporal features. Given a novel video sequence, the model is able to categorize human actions in a frame-by-frame basis. We test the model on a publicly available human action dataset [2] and show that our new method performs well on the classification task. We also conducted control experiments to show that the use of the proposed mixture of hierarchical models improves the classification performance over bag of feature models. An additional experiment shows that using both dynamic and static features provides a richer representation of human actions when compared to the use of a single feature type, as demonstrated by our evaluation in the classification task.