Learning Social Relation Traits from Face Images
This addresses the challenge of quantifying high-level social interactions from visual data, which could benefit fields like psychology and human-computer interaction, though it appears incremental as it builds on existing deep learning methods for attribute prediction.
The paper tackled the problem of characterizing fine-grained social relation traits like warmth and dominance from face images in the wild, proposing a deep model that learns rich face representations and performs pairwise reasoning, with experiments showing effectiveness in images and videos.
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.