Litcius/Paper detail

Visual-Semantic Graph Matching for Visual Grounding

Chenchen Jing, Yuwei Wu, Mingtao Pei, Yao Hu, Yunde Jia, Qi Wu

202035 citationsDOI

Abstract

Visual Grounding is the task of associating entities in a natural language sentence with objects in an image. In this paper, we formulate visual grounding as a graph matching problem to find node correspondences between a visual scene graph and a language scene graph. These two graphs are heterogeneous, representing structure layouts of the sentence and image, respectively. We learn unified contextual node representations of the two graphs by using a cross-modal graph convolutional network to reduce their discrepancy. The graph matching is thus relaxed as a linear assignment problem because the learned node representations characterize both node information and structure information. A permutation loss and a semantic cycle-consistency loss are further introduced to solve the linear assignment problem with or without ground-truth correspondences. Experimental results on two visual grounding tasks, i.e., referring expression comprehension and phrase localization, demonstrate the effectiveness of our method.

Topics & Concepts

Computer scienceArtificial intelligenceSemantic matchingSentenceGraphTheoretical computer scienceNatural language processingPattern recognition (psychology)Matching (statistics)MathematicsStatisticsMultimodal Machine Learning ApplicationsAdvanced Image and Video Retrieval TechniquesHuman Pose and Action Recognition
Visual-Semantic Graph Matching for Visual Grounding | Litcius