Associating Images with Sentences Using Recurrent Canonical Correlation Analysis

doi:10.3390/app10165516

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 先进机器人控制团队

	Associating Images with Sentences Using Recurrent Canonical Correlation Analysis
	Guo, Yawen 3; Yuan, Hui 1,2; Zhang, Kun 2
刊名	APPLIED SCIENCES-BASEL
	2020-08-01
卷号	10 期号:16 页码:14
关键词	image retrieval image and sentence matching canonical correlation analysis
DOI	10.3390/app10165516
通讯作者	Guo, Yawen(yavinguo@outlook.com)
英文摘要	Associating images with sentences has drawn much attention recently. Existing methods commonly represent an image by indistinctively describing all its contents in an one-time static way, which ignores two facts that (1) the association analysis can only be effective for partial salient contents and the associated sentence, and (2) visual information acquisition is a dynamical rather than static process. To deal with this issue, we propose a recurrent canonical correlation analysis (RCCA) method for associating images with sentences. RCCA includes a contextual attention-based LSTM-RNN which can selectively attend to salient regions of an image at each time step, and then represent all the salient contents within a few steps. Different from existing attention-based models, our model focuses on the modelling of contextual visual attention mechanism for the task of association analysis. RCCA also includes a conventional LSTM-RNN for sentence representation learning. The resulting representations of images and sentences are fed into CCA to maximize linear correlation, where parameters of LSTM-RNNs and CCA are jointly learned. Due to the effective image representation learning, our model can well associate images with sentences with complex contents, and achieve better performance in terms of image annotation and retrieval.
WOS研究方向	Chemistry ; Engineering ; Materials Science ; Physics
语种	英语
出版者	MDPI
WOS记录号	WOS:000564772700001
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/41516]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_先进机器人控制团队
通讯作者	Guo, Yawen
作者单位	1.Xiangtan Univ, Coll Automat & Elect Informat, Xiangtan 411105, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Inst Biophys, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Guo, Yawen,Yuan, Hui,Zhang, Kun. Associating Images with Sentences Using Recurrent Canonical Correlation Analysis[J]. APPLIED SCIENCES-BASEL,2020,10(16):14.
APA	Guo, Yawen,Yuan, Hui,&Zhang, Kun.(2020).Associating Images with Sentences Using Recurrent Canonical Correlation Analysis.APPLIED SCIENCES-BASEL,10(16),14.
MLA	Guo, Yawen,et al."Associating Images with Sentences Using Recurrent Canonical Correlation Analysis".APPLIED SCIENCES-BASEL 10.16(2020):14.