arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.03067cs.CV
收藏

基于多粒度推理的图像社会关系识别

Multi-Granularity Reasoning for Social Relation Recognition from Images

Beijing University of Posts and Telecommunications(北京邮电大学);JD AI Research, JD.com(京东集团京东人工智能研究院)

Meng Zhang, Xinchen Liu, Wu Liu, Anfu Zhou, Huadong Ma, Tao Mei

摘要:

发现图像中的社会关系可以让机器更好地解释人类的行为。然而,自动识别图像中的社会关系是一个具有挑战性的任务,由于视觉内容和社会关系的领域之间的显着差距。现有的研究分别处理人脸表情、身体外观和上下文对象等各种特征,因此不能全面地捕获多粒度语义,如场景、人的区域线索以及人与对象之间的交互。为了弥合领域差距,我们提出了一个多粒度推理框架,从图像中识别社会关系。全局知识和中层细节分别从整个场景和区域的人和物体,学习。最重要的是,我们探索细粒度的人的姿势关键点,发现人与物体之间的相互作用。具体地说,姿势引导的人-物图和人-姿势图被提出来建模从人到物体的动作和成对的人之间的交互,分别。在此基础上,利用图卷积网络进行社会关系推理。最后,将全局特征和推理知识结合起来,作为社会关系识别的综合表示。在两个公共数据集上的实验表明了该框架的有效性。

英文摘要:

Discovering social relations in images can make machines better interpret the behavior of human beings. However, automatically recognizing social relations in images is a challenging task due to the significant gap between the domains of visual content and social relation. Existing studies separately process various features such as faces expressions, body appearance, and contextual objects, thus they cannot comprehensively capture the multi-granularity semantics, such as scenes, regional cues of persons, and interactions among persons and objects. To bridge the domain gap, we propose a Multi-Granularity Reasoning framework for social relation recognition from images. The global knowledge and mid-level details are learned from the whole scene and the regions of persons and objects, respectively. Most importantly, we explore the fine-granularity pose keypoints of persons to discover the interactions among persons and objects. Specifically, the pose-guided Person-Object Graph and Person-Pose Graph are proposed to model the actions from persons to object and the interactions between paired persons, respectively. Based on the graphs, social relation reasoning is performed by graph convolutional networks. Finally, the global features and reasoned knowledge are integrated as a comprehensive representation for social relation recognition. Extensive experiments on two public datasets show the effectiveness of the proposed framework.

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。

↑