English

Learning Social Relation Traits from Face Images

Computer Vision and Pattern Recognition 2015-09-15 v1 Computers and Society

Abstract

Social relation defines the association, e.g, warm, friendliness, and dominance, between two or more people. Motivated by psychological studies, we investigate if such fine-grained and high-level relation traits can be characterised and quantified from face images in the wild. To address this challenging problem we propose a deep model that learns a rich face representation to capture gender, expression, head pose, and age-related attributes, and then performs pairwise-face reasoning for relation prediction. To learn from heterogeneous attribute sources, we formulate a new network architecture with a bridging layer to leverage the inherent correspondences among these datasets. It can also cope with missing target attribute labels. Extensive experiments show that our approach is effective for fine-grained social relation learning in images and videos.

Keywords

Cite

@article{arxiv.1509.03936,
  title  = {Learning Social Relation Traits from Face Images},
  author = {Zhanpeng Zhang and Ping Luo and Chen Change Loy and Xiaoou Tang},
  journal= {arXiv preprint arXiv:1509.03936},
  year   = {2015}
}

Comments

To appear in International Conference on Computer Vision (ICCV) 2015

R2 v1 2026-06-22T10:55:36.815Z