Exemplar-Based Recognition of Human–Object Interactions
Exemplar-Based Recognition of Human–Object Interactions
复制标题
DOI：
10.1109/tcsvt.2015.2397200
复制
发表时间：
2016-04
影响因子：
8.4
通讯作者：
Jianfang Hu;Weishi Zheng;J. Lai;S. Gong;T. Xiang
中科院分区：
文献类型：
--
作者：
Jianfang Hu;Weishi Zheng;J. Lai;S. Gong;T. Xiang
通过对人-物交互（HOI）进行建模，可以从单个静止图像中识别出人的动作，从而推断出人与被操纵物体之间的相互空间结构信息以及它们的外观。现有的方法严重依赖于人和对象的准确检测和人的姿态的估计，因此，它们对人的姿态的大变化、遮挡和小尺寸对象的不令人满意的检测敏感。为了克服这一局限性，本文提出了一种新的基于范例的方法。我们的方法学习了一组空间姿态-对象交互范例，这些范例是概率密度函数，描述了一个人在空间上如何与不同活动的操纵对象进行交互。具体而言，一个新的框架，包括一个基于范例的HOI描述符和相关的匹配模型制定了强大的人体动作识别在静止图像。此外，该框架被扩展到在视频中执行HOI识别，其中所提出的示例表示用于隐式帧选择，以通过时间结构化HOI建模来否定不相关或有噪声的帧。在两个图像动作数据集和两个视频动作数据集上进行了广泛的实验。结果表明，我们提出的方法的有效性，并表明，我们的方法是能够实现国家的最先进的性能，与最近提出的几个竞争对手相比。
Human action can be recognized from a single still image by modeling human-object interactions (HOIs), which infers the mutual spatial structure information between human and the manipulated object as well as their appearance. Existing approaches rely heavily on accurate detection of human and object and estimation of human pose; they are thus sensitive to large variations of human poses, occlusion, and unsatisfactory detection of small size objects. To overcome this limitation, a novel exemplar-based approach is proposed in this paper. Our approach learns a set of spatial pose-object interaction exemplars, which are probabilistic density functions describing spatially how a person is interacting with a manipulated object for different activities. Specifically, a new framework consisting of an exemplar-based HOI descriptor and an associated matching model is formulated for robust human action recognition in still images. In addition, the framework is extended to perform HOI recognition in videos, where the proposed exemplar representation is used for implicit frame selection to negate irrelevant or noisy frames by temporal structured HOI modeling. Extensive experiments are carried out on two image action datasets and two video action datasets. The results demonstrate the effectiveness of our proposed methods and show that our approach is able to achieve state-of-the-art performance, compared with several recently proposed competitors.