arxivst stuff from arxiv that you should probably bookmark

Detecting Visual Relationships with Deep Relational Networks

Abstract · Apr 11, 2017 02:11 ·

sit carry relationships objects visual sification phrases genome cs-cv

Arxiv Abstract

  • Bo Dai
  • Yuqi Zhang
  • Dahua Lin

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.

Read the paper (pdf) »