Dong, Zhen; Kong, Yu; Liu, Cuiwei; Li, Hongdong; Jia, Yunde
In this paper, we address the problem of recognizing human interaction of two persons from videos. We fuse global and local features to build a more expressive and discriminative action representation. The representation based on multiple features is robust to motion ambiguity and partial occlusion in interactions. Moreover, action context information is utilized to capture the interdependencies between interaction class and individual action classes of two persons. We introduce a hierarchical...[Show more]
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.