所属单位：[1] Faculty of Information Technology, Monash University, Australia; [2] Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, China

发表刊物：arXiv

关键字：Machine learning

摘要：Despite the huge progress in scene graph generation in recent years, its long-tail distribution in object relationships remains a challenging and pestering issue. Existing methods largely rely on either external knowledge or statistical bias information to alleviate this problem. In this paper, we tackle this issue from another two aspects: (1) scene-object interaction aiming at learning specific knowledge from a scene via an additive attention mechanism; and (2) long-tail knowledge transfer which tries to transfer the rich knowledge learned from the head into the tail. Extensive experiments on the benchmark dataset Visual Genome on three tasks demonstrate that our method outperforms current state-of-the-art competitors. Copyright ? 2020, The Authors. All rights reserved.

文献类型：Preprint (PP)

是否译文：否