Disentangled Motif-aware Graph Learning for Phrase Grounding

• Published in: arXiv.org
• Main Authors: Mu, Zongshen, Tang, Siliang, Tan, Jie, Yu, Qiang, Zhuang, Yueting
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 13.04.2021
• Subjects: Ablation; Context; Image contrast; Learning; Representations

In this paper, we propose a novel graph learning framework for phrase grounding in the image. Developing from the sequential to the dense graph model, existing works capture coarse-grained context but fail to distinguish the diversity of context among phrases and image regions. In contrast, we pay s...