Visual Madlibs: Fill in the blank Description Generation and Question Answering

被引：96

作者：

Yu, Licheng ^{[1
]}

Park, Eunbyung ^{[1
]}

Berg, Alexander C. ^{[1
]}

Berg, Tamara L. ^{[1
]}

机构：

[1] Univ N Carolina, Dept Comp Sci, Chapel Hill, NC 27599 USA

来源：

2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) | 2015年

基金：

美国国家科学基金会;

关键词：

D O I：

10.1109/ICCV.2015.283

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we introduce a new dataset consisting of 360,001 focused natural language descriptions for 10,738 images. This dataset, the Visual Madlibs dataset, is collected using automatically produced fill-in-the-blank templates designed to gather targeted descriptions about: people and objects, their appearances, activities, and interactions, as well as inferences about the general scene or its broader context. We provide several analyses of the Visual Madlibs dataset and demonstrate its applicability to two new description generation tasks: focused description generation, and multiple-choice question-answering for images. Experiments using joint-embedding and deep learning methods show promising results on these tasks.

引用

页码：2461 / 2469

页数：9