2015/09/14 by Zhanpeng Zhang, Zhang, Zhanpeng, Ping Luo +5 · 28 citations
Computer Science · Neuroscience · Psychology · #Architecture #Artificial intelligence #Association (psychology) #Bridging (networking) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computers and Society (cs.CY) #Contrast (vision) #Data mining #FOS: Computer and information sciences #Face (sociological concept) #Face Recognition and Perception #Face recognition and analysis #Generative Adversarial Networks and Image Synthesis #Geography #Leverage (statistics) #Machine learning #Pairwise comparison #Psychology #Relation (database) #Representation (politics) #Sociology #cs.CV #cs.CY
paper · pdf · doi:10.48550/arxiv.1509.03936
published in arXiv (Cornell University) (Cornell University) · To appear in International Conference on Computer Vision (ICCV) 2015
arxiv created 2015/09/14 · openalex publication_date 2015/09/14 · arxiv updated 2015/09/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06
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.