Modeling Context in Referring Expressions

被引：676

作者：

Yu, Licheng ^{[1
]}

Poirson, Patrick ^{[1
]}

Yang, Shan ^{[1
]}

Berg, Alexander C. ^{[1
]}

Berg, Tamara L. ^{[1
]}

机构：

[1] Univ North Carolina Chapel Hill, Dept Comp Sci, Chapel Hill, NC 27514 USA

来源：

COMPUTER VISION - ECCV 2016, PT II | 2016年 / 9906卷

基金：

美国国家科学基金会;

关键词：

Language; Language and vision; Generation; Referring expression generation;

D O I：

10.1007/978-3-319-46475-6_5

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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 (Datasets and toolbox can be downloaded from https://github.com/lichengunc/refer), shows the advantages of our methods for both referring expression generation and comprehension.

引用

页码：69 / 85

页数：17