Adding Chinese Captions to Images

被引：40

作者：

Li, Xirong ^{[1
]}

Lan, Weiyu ^{[1
]}

Dong, Jianfeng ^{[2
]}

Liu, Hailong ^{[3
]}

机构：

[1] Renmin Univ China, Key Lab Data Engn & Knowledge Engn, Haidian Qu, Peoples R China

[2] Zhejiang Univ, Coll Comp Sci & Technol, Hangzhou Shi, Zhejiang Sheng, Peoples R China

[3] Tencent, WeChat Dept, Pattern Recognit Ctr, Shenzhen, Peoples R China

来源：

ICMR'16: PROCEEDINGS OF THE 2016 ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL | 2016年

关键词：

Image captioning; Bilingual dataset; Chinese language;

D O I：

10.1145/2911996.2912049

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

This paper extends research on automated image captioning in the dimension of language, studying how to generate Chinese sentence descriptions for unlabeled images. To evaluate image captioning in this novel context, we present Flickr8k-CN, a bilingual extension of the popular Flickr8k set. The new multimedia dataset can be used to quantitatively assess the performance of Chinese captioning and English-Chinese machine translation. The possibility of reusing existing English data and models via machine translation is investigated. Our study reveals to some extent that a computer can master two distinct languages, English and Chinese, at a similar level for describing the visual world. Data is publicly available at http://tinyurl.com/flickr8kcn.

引用

页码：271 / 275

页数：5