The Community for Technology Leaders
2017 IEEE International Conference on Computer Vision (ICCV) (2017)
Venice, Italy
Oct. 22, 2017 to Oct. 29, 2017
ISSN: 2380-7504
ISBN: 978-1-5386-1032-9
pp: 2669-2678
ABSTRACT
Since the beginning of early civilizations, social relationships derived from each individual fundamentally form the basis of social structure in our daily life. In the computer vision literature, much progress has been made in scene understanding, such as object detection and scene parsing. Recent research focuses on the relationship between objects based on its functionality and geometrical relations. In this work, we aim to study the problem of social relationship recognition, in still images. We have proposed a dual-glance model for social relationship recognition, where the first glance fixates at the individual pair of interest and the second glance deploys attention mechanism to explore contextual cues. We have also collected a new large scale People in Social Context (PISC) dataset, which comprises of 22,670 images and 76,568 annotated samples from 9 types of social relationship. We provide benchmark results on the PISC dataset, and qualitatively demonstrate the efficacy of the proposed model.
INDEX TERMS
computer vision, image recognition, image segmentation, object detection, social networking (online), social sciences computing
CITATION

J. Li, Y. Wong, Q. Zhao and M. S. Kankanhalli, "Dual-Glance Model for Deciphering Social Relationships," 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2018, pp. 2669-2678.
doi:10.1109/ICCV.2017.289
84 ms
(Ver 3.3 (11022016))