From Facial Expression Recognition to Interpersonal Relation Prediction
This addresses the challenge of quantifying high-level social traits from images for applications in psychology and human-computer interaction, representing an incremental advance by building on expression recognition with new multitask and propagation techniques.
The paper tackled the problem of predicting fine-grained interpersonal relations from face images by first developing a multitask network for facial expression recognition that leverages auxiliary attributes and a novel attribute propagation method, achieving state-of-the-art results on benchmarks, and then using it in a Siamese model to accurately predict relations like warmth and dominance.
Interpersonal 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 characterized and quantified from face images in the wild. We address this challenging problem by first studying a deep network architecture for robust recognition of facial expressions. Unlike existing models that typically learn from facial expression labels alone, we devise an effective multitask network that is capable of learning from rich auxiliary attributes such as gender, age, and head pose, beyond just facial expression data. While conventional supervised training requires datasets with complete labels (e.g., all samples must be labeled with gender, age, and expression), we show that this requirement can be relaxed via a novel attribute propagation method. The approach further allows us to leverage the inherent correspondences between heterogeneous attribute sources despite the disparate distributions of different datasets. With the network we demonstrate state-of-the-art results on existing facial expression recognition benchmarks. To predict inter-personal relation, we use the expression recognition network as branches for a Siamese model. Extensive experiments show that our model is capable of mining mutual context of faces for accurate fine-grained interpersonal prediction.