Interactive Phrases: Semantic Descriptions for Human Interaction Recognition
Interactive Phrases: Semantic Descriptions for Human Interaction Recognition
复制标题
交互短语：人类交互识别的语义描述
DOI：
10.1109/tpami.2014.2303090
复制
发表时间：
2014
影响因子：
23.6
通讯作者：
Fu Yun
中科院分区：
文献类型：
--
作者：
Kong Yu;Jia Yunde;Fu Yun
本文研究了从视频中识别人类交互的问题。我们提出了一种新的方法，通过学习高层描述、交互短语来识别人类交互。互动短语描述了相互作用的人之间的运动关系。这些短语自然地利用了人类的知识，并允许我们构建一个更具描述性的模型来识别人类的互动。提出了一种基于潜在支持向量机的交互短语识别模型。交互短语被视为潜在变量，并被用作中层特征。为了补充人工指定的交互短语，我们还从数据中发现数据驱动的短语，以便找到潜在的有用和区分人类交互的短语。使用信息论的方法学习数据驱动的短语。该模型显式地捕捉了交互短语之间的相互依赖关系，以处理交互中的运动模糊和部分遮挡。我们在比特交互数据集、UT交互数据集和集合活动数据集上对我们的方法进行了评估。实验结果表明，该方法取得了优于以往方法的性能。
This paper addresses the problem of recognizing human interactions from videos. We propose a novel approach that recognizes human interactions by the learned high-level descriptions, interactive phrases. Interactive phrases describe motion relationships between interacting people. These phrases naturally exploit human knowledge and allow us to construct a more descriptive model for recognizing human interactions. We propose a discriminative model to encode interactive phrases based on the latent SVM formulation. Interactive phrases are treated as latent variables and are used as mid-level features. To complement manually specified interactive phrases, we also discover data-driven phrases from data in order to find potentially useful and discriminative phrases for differentiating human interactions. An information-theoretic approach is employed to learn the data-driven phrases. The interdependencies between interactive phrases are explicitly captured in the model to deal with motion ambiguity and partial occlusion in the interactions. We evaluate our method on the BIT-Interaction data set, UT-Interaction data set, and Collective Activity data set. Experimental results show that our approach achieves superior performance over previous approaches.