Detecting Visual Relationships with Deep Relational Networks

• DOI: 10.48550/arxiv.1704.03114
• Publication Date: 2017-01-01
• Authors: Bo Dai; Yuqi Zhang; Dahua Lin
• Keywords: Phrase

Relationships among objects play a crucial role in image understanding. Despite the great success of deep learning techniques recognizing individual objects, reasoning about relationships remains challenging task. Previous methods often treat this as classification problem, considering each type relationship (e.g. "ride") or distinct visual phrase "person-ride-horse") category. Such approaches are faced with significant difficulties caused by high diversity appearance for kind large number phrases. We propose an integrated framework to tackle problem. At heart is Deep Relational Network, novel formulation designed specifically exploiting statistical dependencies between and their relationships. On two datasets, proposed method achieves substantial improvement over state-of-the-art.