Unsupervised Cross-Modal Hashing via Semantic Text Mining

doi:10.1109/TMM.2023.3243608

CSpace

	Unsupervised Cross-Modal Hashing via Semantic Text Mining
	Tu, Rong-Cheng 1; Mao, Xian-Ling 1; Lin, Qinghong 2; Ji, Wenjin 1; Qin, Weize 3; Wei, Wei 4; Huang, Heyan 1
	2023
发表期刊	IEEE TRANSACTIONS ON MULTIMEDIA
ISSN	1520-9210
卷号	25 页码:8946-8957
摘要	Cross-modal hashing has been widely used in multimedia retrieval tasks due to its fast retrieval speed and low storage cost. Recently, many deep unsupervised cross-modal hashing methods have been proposed to deal the unlabeled datasets. These methods usually construct an instance similarity matrix by fusing the image and text modality-specific similarity matrices as the guiding information to train the hashing networks. However, most of them directly use cosine similarities between the bag-of-words (BoW) vectors of text datapoints to define the text modality-specific similarity matrix, which fails to mine the semantic similarity information contained in the text modal datapoints and leads to the poor quality of the instance similarity matrix. To tackle the aforementioned problem, in this paper, we propose a novel Unsupervised Cross-modal Hashing via Semantic Text Mining, called UCHSTM. Specifically, UCHSTM first mines the correlations between the words of text datapoints. Then, UCHSTM constructs the text modality-specific similarity matrix for the training instances based on the mined correlations between their words. Next, UCHSTM fuses the image and text modality-specific similarity matrices as the final instance similarity matrix to guide the training of hashing model. Furthermore, during the process of training the hashing networks, a novel self-redefined-similarity loss is proposed to further correct some wrong defined similarities in the constructed instance similarity matrix, thereby further enhancing the retrieval performance. Extensive experiments on two widely used datasets show that the proposed UCHSTM outperforms state-of-the-art baselines on cross-modal retrieval tasks.
关键词	Cross-modal retrieval deep supervised hashing semantic text mining self-redefined-similarity loss
DOI	10.1109/TMM.2023.3243608
收录类别	SCI
语种	英语
资助项目	National Key Ramp;D Plan
WOS研究方向	Computer Science ; Telecommunications
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
WOS记录号	WOS:001133278300011
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：7[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/38414
专题	中国科学院计算技术研究所
通讯作者	Mao, Xian-Ling
作者单位	1.Beijing Inst Technol, Dept Comp Sci & Technol, Beijing 100081, Peoples R China 2.Shenzhen Univ, Sch Comp Sci & Software Engn, Shenzhen 518052, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 4.Huazhong Univ Sci & Technol, Sch Comp Sci & Technol, Wuhan 430074, Peoples R China
推荐引用方式 GB/T 7714	Tu, Rong-Cheng,Mao, Xian-Ling,Lin, Qinghong,et al. Unsupervised Cross-Modal Hashing via Semantic Text Mining[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2023,25:8946-8957.
APA	Tu, Rong-Cheng.,Mao, Xian-Ling.,Lin, Qinghong.,Ji, Wenjin.,Qin, Weize.,...&Huang, Heyan.(2023).Unsupervised Cross-Modal Hashing via Semantic Text Mining.IEEE TRANSACTIONS ON MULTIMEDIA,25,8946-8957.
MLA	Tu, Rong-Cheng,et al."Unsupervised Cross-Modal Hashing via Semantic Text Mining".IEEE TRANSACTIONS ON MULTIMEDIA 25(2023):8946-8957.