arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1404.4923cs.CV
收藏

基于统一结构学习的人体姿态估计与服装属性分类

Unified Structured Learning for Simultaneous Human Pose Estimation and Garment Attribute Classification

Shanghai Jiao Tong University(上海交通大学);Nanjing University of Information Science and Technology(南京信息工程大学);National University of Defense Technology(国防科技大学);National University of Singapore(新加坡国立大学)

Jie Shen, Guangcan Liu, Jia Chen, Yuqiang Fang, Jianbin Xie, Yong Yu, Shuicheng Yan

摘要:

在本文中,我们利用结构化学习,同时解决两个相互交织的问题:人体姿态估计(HPE)和服装属性分类(GAC),这是有价值的各种计算机视觉和多媒体应用。与以前的作品,通常单独处理这两个问题,我们的方法的目的是通过一个统一的推理过程,产生一个联合最优估计HPE和GAC。为此,我们采用预处理步骤来从每个图像中检测潜在的人体部位(即,一组“候选者”),这允许我们拥有一个可管理的输入空间。通过这种方式,HPE和GAC的同时推理被转换为结构化学习问题,其中输入是候选集合的集合,输出是人体部位和服装属性的联合标签,并且联合特征表示涉及各种线索,例如姿势特定特征、服装特定特征以及编码人体部位和服装属性之间的相关性的跨任务特征。此外,我们探索的“强边缘”的证据周围的潜在的人体部位,以获得更强大的表示面向人体部位。这些证据可以无缝地集成到我们的结构化学习模型作为一种能量函数,学习过程中可以执行标准的结构化支持向量机(SVM)算法。然而,这两个问题的联合结构是一个循环图,这阻碍了有效的推理。为了解决这个问题,我们使用迭代过程来计算近似最优解,其中在每次迭代中,一个问题的变量是固定的。通过这种方式,可以通过动态规划有效地计算满意解。在两个基准数据集上的实验结果显示了我们方法的最新性能。

英文摘要:

In this paper, we utilize structured learning to simultaneously address two intertwined problems: human pose estimation (HPE) and garment attribute classification (GAC), which are valuable for a variety of computer vision and multimedia applications. Unlike previous works that usually handle the two problems separately, our approach aims to produce a jointly optimal estimation for both HPE and GAC via a unified inference procedure. To this end, we adopt a preprocessing step to detect potential human parts from each image (i.e., a set of "candidates") that allows us to have a manageable input space. In this way, the simultaneous inference of HPE and GAC is converted to a structured learning problem, where the inputs are the collections of candidate ensembles, the outputs are the joint labels of human parts and garment attributes, and the joint feature representation involves various cues such as pose-specific features, garment-specific features, and cross-task features that encode correlations between human parts and garment attributes. Furthermore, we explore the "strong edge" evidence around the potential human parts so as to derive more powerful representations for oriented human parts. Such evidences can be seamlessly integrated into our structured learning model as a kind of energy function, and the learning process could be performed by standard structured Support Vector Machines (SVM) algorithm. However, the joint structure of the two problems is a cyclic graph, which hinders efficient inference. To resolve this issue, we compute instead approximate optima by using an iterative procedure, where in each iteration the variables of one problem are fixed. In this way, satisfactory solutions can be efficiently computed by dynamic programming. Experimental results on two benchmark datasets show the state-of-the-art performance of our approach.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑