Learning Human Interaction by Interactive Phrases

Yu Kong^1,3, Yunde Jia¹, and Yun Fu²

¹Beijing Laboratory of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology, Beijing 100081, P.R. China
kongyu@bit.edu.cn
jiayunde@bit.edu.cn

²Department of ECE and College of CIS, Northeastern University, Boston, MA, USA
y.fu@neu.edu

³Department of CSE, State University of New York, Buffalo, NY, USA

Abstract. In this paper, we present a novel approach for human interaction recognition from videos. We introduce high-level descriptions called interactive phrases to express binary semantic motion relationships between interacting people. Interactive phrases naturally exploit human knowledge to describe interactions and allow us to construct a more descriptive model for recognizing human interactions. We propose a novel hierarchical model to encode interactive phrases based on the latent SVM framework where interactive phrases are treated as latent variables. The interdependencies between interactive phrases are explicitly captured in the model to deal with motion ambiguity and partial occlusion in interactions. We evaluate our method on a newly collected BIT-Interaction dataset and UT-Interaction dataset. Promising results demonstrate the effectiveness of the proposed method.

LNCS 7572, p. 300 ff.

Full article in PDF | BibTeX

lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2012