2017/04/11 by Bo Dai, Yuqi Zhang, Dai, Bo +3 · 26 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Domain Adaptation and Few-Shot Learning #Multimodal Machine Learning Applications #cs.CV
paper · pdf · doi:10.48550/arxiv.1704.03114
To be appeared in CVPR 2017 as an oral paper
arxiv created 2017/04/12 · arxiv updated 2017/04/13
Relationships among objects play a crucial role in image understanding. Despite the great success of deep learning techniques in recognizing individual objects, reasoning about the relationships among objects remains a challenging task. Previous methods often treat this as a classification problem, considering each type of relationship (e.g. "ride") or each distinct visual phrase (e.g. "person-ride-horse") as a category. Such approaches are faced with significant difficulties caused by the high diversity of visual appearance for each kind of relationships or the large number of distinct visual phrases. We propose an integrated framework to tackle this problem. At the heart of this framework is the Deep Relational Network, a novel formulation designed specifically for exploiting the statistical dependencies between objects and their relationships. On two large datasets, the proposed method achieves substantial improvement over state-of-the-art.