Dense semantic embedding network for image captioning

doi:10.1016/j.patcog.2019.01.028

	Dense semantic embedding network for image captioning
	Xiao, Xinyu1,2 ; Wang, Lingfeng1 ; Ding, Kun1 ; Xiang, Shiming1,2 ; Pan, Chunhong1
刊名	PATTERN RECOGNITION
	2019-06-01
卷号	90 页码:285-296
关键词	Image captioning Retrieval High-level semantic information Visual concept Densely embedding Long short-term memory
ISSN号	0031-3203
DOI	10.1016/j.patcog.2019.01.028
通讯作者	Xiao, Xinyu(xinyu.xiao@nlpr.ia.ac.cn)
英文摘要	Recently, 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.
资助项目	National 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]
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	ELSEVIER SCI LTD
WOS记录号	WOS:000463130400024
资助机构	National Natural Science Foundation of China ; Beijing Natural Science Foundation
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/23492]
专题	中国科学院自动化研究所
通讯作者	Xiao, Xinyu
作者单位	1.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
推荐引用方式 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.