CASIA OpenIR
Dense semantic embedding network for image captioning
Xiao, Xinyu1,2; Wang, Lingfeng1; Ding, Kun1; Xiang, Shiming1,2; Pan, Chunhong1
Source PublicationPATTERN RECOGNITION
ISSN0031-3203
2019-06-01
Volume90Pages:285-296
Corresponding AuthorXiao, Xinyu(xinyu.xiao@nlpr.ia.ac.cn)
AbstractRecently, attributes that contain high-level semantic information of image are always used as a complementary knowledge to improve image captioning performance. However, the use of attributes in prior works cannot excavate the latent visual concepts effectively. At each time step, the semantic information which is sensitive to the predicted word could be different. In this paper, we propose a Dense Semantic Embedding Network (DSEN) for this task. The distinct operation of this network is to densely embed the attributes with the multi-modal of image and text at each step of word generation. The discriminative semantic information hidden in these attributes is formatted in form of global likelihood probabilities. As a result, this dense embedding can modulate the feature distributions of the image, text modals and the hidden states to explicit semantic representation. Furthermore, to improve the discrimination of attributes, a Threshold ReLU (TReLU) is proposed. In addition, a bidirectional LSTM structure is incorporated into the DSEN to capture both the previous and future contexts. Extensive experiments on the COCO and Flickr30K datasets achieve superior results when compared with the state-of-the-art models for the tasks of both image captioning and image-text cross modal retrieval. Most remarkably, our method obtains outstanding performance on the retrieval task, compared with the state-of-the-art models. (C) 2019 Published by Elsevier Ltd.
KeywordImage captioning Retrieval High-level semantic information Visual concept Densely embedding Long short-term memory
DOI10.1016/j.patcog.2019.01.028
Indexed BySCI
Language英语
Funding ProjectNational Natural Science Foundation of China[91646207] ; National Natural Science Foundation of China[61773377] ; National Natural Science Foundation of China[61573352] ; Beijing Natural Science Foundation[4162064] ; Beijing Natural Science Foundation[L172053]
Funding OrganizationNational Natural Science Foundation of China ; Beijing Natural Science Foundation
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000463130400024
PublisherELSEVIER SCI LTD
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23493
Collection中国科学院自动化研究所
Corresponding AuthorXiao, Xinyu
Affiliation1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Xiao, Xinyu,Wang, Lingfeng,Ding, Kun,et al. Dense semantic embedding network for image captioning[J]. PATTERN RECOGNITION,2019,90:285-296.
APA Xiao, Xinyu,Wang, Lingfeng,Ding, Kun,Xiang, Shiming,&Pan, Chunhong.(2019).Dense semantic embedding network for image captioning.PATTERN RECOGNITION,90,285-296.
MLA Xiao, Xinyu,et al."Dense semantic embedding network for image captioning".PATTERN RECOGNITION 90(2019):285-296.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Xiao, Xinyu]'s Articles
[Wang, Lingfeng]'s Articles
[Ding, Kun]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xiao, Xinyu]'s Articles
[Wang, Lingfeng]'s Articles
[Ding, Kun]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xiao, Xinyu]'s Articles
[Wang, Lingfeng]'s Articles
[Ding, Kun]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.