Graph-Based Social Relation Reasoning
This work addresses social relation understanding for intelligent systems like chatbots and assistants, but it appears incremental as it builds on existing methods by adding graph-based reasoning.
The paper tackles social relation recognition from images by proposing a graph relational reasoning network (GR2N) that jointly infers relations using a social relation graph, resulting in improved accuracy and efficiency.
Human beings are fundamentally sociable -- that we generally organize our social lives in terms of relations with other people. Understanding social relations from an image has great potential for intelligent systems such as social chatbots and personal assistants. In this paper, we propose a simpler, faster, and more accurate method named graph relational reasoning network (GR2N) for social relation recognition. Different from existing methods which process all social relations on an image independently, our method considers the paradigm of jointly inferring the relations by constructing a social relation graph. Furthermore, the proposed GR2N constructs several virtual relation graphs to explicitly grasp the strong logical constraints among different types of social relations. Experimental results illustrate that our method generates a reasonable and consistent social relation graph and improves the performance in both accuracy and efficiency.