Modeling Context in Referring Expressions

TL;DR

This paper improves the generation and understanding of referring expressions in images by incorporating visual context and joint object modeling, leading to significant performance gains on multiple datasets.

Contribution

It introduces methods that incorporate visual comparison and joint generation for objects, enhancing referring expression models.

Findings

Visual comparison improves model performance

Joint generation for objects enhances expression quality

Methods outperform previous approaches on three datasets

Abstract

Humans refer to objects in their environments all the time, especially in dialogue with other people. We explore generating and comprehending natural language referring expressions for objects in images. In particular, we focus on incorporating better measures of visual context into referring expression models and find that visual comparison to other objects within an image helps improve performance significantly. We also develop methods to tie the language generation process together, so that we generate expressions for all objects of a particular category jointly. Evaluation on three recent datasets - RefCOCO, RefCOCO+, and RefCOCOg, shows the advantages of our methods for both referring expression generation and comprehension.