Learning Cross-modal Context Graph for Visual Grounding

Abstract

Visual grounding is a ubiquitous building block in many vision-language tasks and yet remains challenging due to large variations in visual and linguistic features of grounding entities, strong context effect and the resulting semantic ambiguities. Prior works typically focus on learning representations of individual phrases with limited context information. To address their limitations, this paper proposes a language-guided graph representation to capture the global context of grounding entities and their relations, and develop a cross-modal graph matching strategy for the multiple-phrase visual grounding task. In particular, we introduce a modular graph neural network to compute context-aware representations of phrases and object proposals respectively via message propagation, followed by a graph-based matching module to generate globally consistent localization of grounding phrases. We train the entire graph neural network jointly in a two-stage strategy and evaluate it on the Flickr30K Entities benchmark. Extensive experiments show that our method outperforms the prior state of the arts by a sizable margin, evidencing the efficacy of our grounding framework. Code is available at "https://github.com/youngfly11/LCMCG-PyTorch".

AAAI-2020

References in corpus (9)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
• Visual Translation Embedding Network for Visual Relation Detection
• Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models
• Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods
• Language-Conditioned Graph Networks for Relational Reasoning
• MUREL: Multimodal Relational Reasoning for Visual Question Answering
• Scene Graph Parsing as Dependency Parsing