中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Unsupervised Cross-Modal Hashing via Semantic Text Mining

文献类型：期刊论文

作者Tu, Rong-Cheng4; Mao, Xian-Ling4; Lin, Qinghong3; Ji, Wenjin4; Qin, Weize2; Wei, Wei1; Huang, Heyan4
刊名IEEE TRANSACTIONS ON MULTIMEDIA
出版日期2023
卷号25页码:8946-8957
关键词Cross-modal retrieval deep supervised hashing semantic text mining self-redefined-similarity loss
ISSN号1520-9210
DOI10.1109/TMM.2023.3243608
英文摘要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.
资助项目National Key Ramp;D Plan
WOS研究方向Computer Science ; Telecommunications
语种英语
WOS记录号WOS:001133278300011
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/38413]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Mao, Xian-Ling
作者单位1.Huazhong Univ Sci & Technol, Sch Comp Sci & Technol, Wuhan 430074, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
3.Shenzhen Univ, Sch Comp Sci & Software Engn, Shenzhen 518052, Peoples R China
4.Beijing Inst Technol, Dept Comp Sci & Technol, Beijing 100081, 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.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

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。