Human action recognition by learning bases of action attributes and parts
Human action recognition by learning bases of action attributes and parts
复制标题
DOI：
10.1109/iccv.2011.6126386
复制
发表时间：
2011-11
期刊：
影响因子：
--
通讯作者：
Bangpeng Yao;Xiaoye Jiang;A. Khosla;A. Lin;L. Guibas;Li Fei-Fei-Li-Fei-Fei-48004138
中科院分区：
文献类型：
--
作者：
Bangpeng Yao;Xiaoye Jiang;A. Khosla;A. Lin;L. Guibas;Li Fei-Fei-Li-Fei-Fei-48004138
在这项工作中，我们提出使用属性和部件来识别静止图像中的人体动作。我们将动作属性定义为描述人类动作属性的动词，而动作的部分是与动作密切相关的对象和偏态。我们通过学习一组稀疏基来联合建模属性和部件，这些稀疏基被证明具有很多语义。然后，可以从相对于学习的基础的稀疏系数重建动作图像的属性和部分。这种双重稀疏性为我们的基学习和特征重构方法提供了理论保障。在Pascal动作数据集和一个新的“Stanford 40 Actions”数据集上，我们的方法在获得最先进的分类性能的同时，提取了人类动作中属性和部分之间有意义的高阶交互作用。
In this work, we propose to use attributes and parts for recognizing human actions in still images. We define action attributes as the verbs that describe the properties of human actions, while the parts of actions are objects and poselets that are closely related to the actions. We jointly model the attributes and parts by learning a set of sparse bases that are shown to carry much semantic meaning. Then, the attributes and parts of an action image can be reconstructed from sparse coefficients with respect to the learned bases. This dual sparsity provides theoretical guarantee of our bases learning and feature reconstruction approach. On the PASCAL action dataset and a new “Stanford 40 Actions” dataset, we show that our method extracts meaningful high-order interactions between attributes and parts in human actions while achieving state-of-the-art classification performance.