A supervised dictionary learning and discriminative weighting model for action recognition
A supervised dictionary learning and discriminative weighting model for action recognition
复制标题
DOI：
10.1016/j.neucom.2015.01.024
复制
发表时间：
2015-06
期刊：
影响因子：
6
通讯作者：
Jian Dong;Changyin Sun;Wankou Yang
中科院分区：
文献类型：
--
作者：
Jian Dong;Changyin Sun;Wankou Yang
在本文中，我们提出了一种用于静态图像中动作识别的监督字典学习算法，然后采用区分加权模型。字典学习的基础上，考虑到当地的流形结构和歧视信息的本地描述符的本地Fisher歧视。在字典学习和稀疏编码阶段都考虑了局部描述符的标签信息，从而产生了一种有监督的稀疏编码算法，使得编码系数具有区分性。代替使用空间金字塔特征，基于滑动窗口的具有最大池化的特征从编码系数计算。然后提出了一种结合最大间隔分类器的判别加权模型。加权系数和模型参数可以使用与多核学习算法相同的方式联合学习。我们在以下动作识别数据集上验证了我们的模型：杨柳7人类动作数据集，People Playing Music Instrument（PPMI）数据集和Sports数据集。为了展示我们模型的通用性，我们还在Scene15数据集上对其进行了验证。实验结果表明，该算法仅使用单尺度局部描述符，就可以达到与现有算法相当的效果。
In this paper, we propose a supervised dictionary learning algorithm for action recognition in still images followed by a discriminative weighting model. The dictionary is learned based on Local Fisher Discrimination which takes into account the local manifold structure and discrimination information of local descriptors. The label information of local descriptors is considered in both dictionary learning and sparse coding stage which generates a supervised sparse coding algorithm and makes the coding coefficients discriminative. Instead of using spatial pyramid features, sliding window-based features with max-pooling are computed from coding coefficients. And then a discriminative weighting model combining a max-margin classifier is proposed using the features. Both the weighting coefficients and model parameters can be jointly learned using the same way in Multiple Kernel Learning algorithm. We validate our model on the following action recognition datasets: Willow 7 human actions dataset, People Playing Music Instrument (PPMI) dataset, and Sports dataset. To show the generality of our model, we also validate it on Scene15 dataset. The experiment results show that only with single scale local descriptors, our algorithm is comparable to some state-of-the-art algorithms.