Scene Graph Generation With Hierarchical Context
IEEE Transactions on Neural Networks and Learning Systems(2021)
摘要
Scene graph generation has received increasing attention in recent years. Enhancing the predicate representations is an important entry point to this task. There are various methods to fully investigate the context of representation enhancement. In this brief, we analyze the decisive factors that can significantly affect the relation detection results. Our analysis shows that spatial correlations between objects, focused regions of objects, and global hints related to the relations have strong influences in relation prediction and contradiction elimination. Based on our analysis, we propose a hierarchical context network (HCNet) to generate a scene graph. HCNet consists of three contexts, including interaction context, depression context, and global context, which integrates information from pair, object, and graph levels. The experiments show that our method outperforms the state-of-the-art methods on the Visual Genome (VG) data set.
更多查看译文
关键词
Attention mechanism,context aggregation,scene graph generation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络