Captioning Transformer with Stacked Attention Modules
Zhu, Xinxin1,2,4; Li, Lixiang1,2; Liu, Jing3; Peng, Haipeng1,2; Niu, Xinxin1,2
2018-05-01
发表期刊APPLIED SCIENCES-BASEL
卷号8期号:5
文章类型Article
摘要Image captioning is a challenging task. Meanwhile, it is important for the machine to understand the meaning of an image better. In recent years, the image captioning usually use the long-short-term-memory (LSTM) as the decoder to generate the sentence, and these models show excellent performance. Although the LSTM can memorize dependencies, the LSTM structure has complicated and inherently sequential across time problems. To address these issues, recent works have shown benefits of the Transformer for machine translation. Inspired by their success, we develop a Captioning Transformer (CT) model with stacked attention modules. We attempt to introduce the Transformer to the image captioning task. The CT model contains only attention modules without the dependencies of the time. It not only can memorize dependencies between the sequence but also can be trained in parallel. Moreover, we propose the multi-level supervision to make the Transformer achieve better performance. Extensive experiments are carried out on the challenging MSCOCO dataset and the proposed Captioning Transformer achieves competitive performance compared with some state-of-the-art methods.
关键词Image Caption Image Understanding Deep Learning Computer Vision
WOS标题词Science & Technology ; Physical Sciences ; Technology
DOI10.3390/app8050739
收录类别SCI
语种英语
项目资助者National Key R&D Program of China(2016YFB0800602) ; National Natural Science Foundation of China(61472045 ; 61573067)
WOS研究方向Chemistry ; Materials Science ; Physics
WOS类目Chemistry, Multidisciplinary ; Materials Science, Multidisciplinary ; Physics, Applied
WOS记录号WOS:000437326800086
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/21853
专题模式识别国家重点实验室_图像与视频分析
作者单位1.Beijing Univ Posts & Telecommun, State Key Lab Networking & Switching Technol, Informat Secur Ctr, Beijing 100876, Peoples R China
2.Beijing Univ Posts & Telecommun, Natl Engn Lab Disaster Backup & Recovery, Beijing 100876, Peoples R China
3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
4.Beijing Univ Posts & Telecommun, Sch Cyberspace Secur, POB 145, Beijing 100876, Peoples R China
推荐引用方式
GB/T 7714
Zhu, Xinxin,Li, Lixiang,Liu, Jing,et al. Captioning Transformer with Stacked Attention Modules[J]. APPLIED SCIENCES-BASEL,2018,8(5).
APA Zhu, Xinxin,Li, Lixiang,Liu, Jing,Peng, Haipeng,&Niu, Xinxin.(2018).Captioning Transformer with Stacked Attention Modules.APPLIED SCIENCES-BASEL,8(5).
MLA Zhu, Xinxin,et al."Captioning Transformer with Stacked Attention Modules".APPLIED SCIENCES-BASEL 8.5(2018).
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhu, Xinxin]的文章
[Li, Lixiang]的文章
[Liu, Jing]的文章
百度学术
百度学术中相似的文章
[Zhu, Xinxin]的文章
[Li, Lixiang]的文章
[Liu, Jing]的文章
必应学术
必应学术中相似的文章
[Zhu, Xinxin]的文章
[Li, Lixiang]的文章
[Liu, Jing]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。