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. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 多媒体计算与图形学团队
Multi-Level Correlation Adversarial Hashing for Cross-Modal Retrieval

文献类型：期刊论文

作者Ma, Xinhong1,3,4; Zhang, Tianzhu2; Xu, Changsheng1,3,4
刊名IEEE TRANSACTIONS ON MULTIMEDIA
出版日期2020-12-01
卷号22期号:12页码:3101-3114
ISSN号1520-9210
关键词Semantics Correlation Aircraft propulsion Deep learning Bridges Aircraft Task analysis Cross-modal retrieval adversarial hashing multi-level correlation
DOI10.1109/TMM.2020.2969792
通讯作者Xu, Changsheng(csxu@nlpr.ia.ac.cn)
英文摘要Cross-modal hashing (CMH) has been widely used for similarity search in multimedia retrieval applications, thanks to low storage cost and fast query speed. However, preserving the content similarities in finite-length hash codes between different data modalities is still challenging due to the existing heterogeneity gap. To further address the crucial bottleneck, we propose a Multi-Level Correlation Adversarial Hashing (MLCAH) algorithm to integrate the multi-level correlation information into hash codes. The proposed MLCAH model enjoys several merits. First, to the best of our knowledge, it is the early attempt of leveraging the multi-level correlation information for cross-modal hashing retrieval. Second, we propose global and local semantic alignment mechanisms, which can effectively encode multi-level correlation information, including global information, local information, and label information into hash codes. Third, a label-consistency attention mechanism with adversarial training is designed for exploiting the local cross-modality similarity from multi-modality data. Extensive evaluations on four benchmarks demonstrate that the proposed model brings significant improvements over several state-of-the-art cross-modal hashing methods.
WOS关键词REPRESENTATION ; CODES ; RANK
资助项目National Natural Science Foundation of China[61720106006] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[61832002] ; National Natural Science Foundation of China[61532009] ; National Natural Science Foundation of China[U1705262] ; National Natural Science Foundation of China[U1836220] ; National Natural Science Foundation of China[61702511] ; National Natural Science Foundation of China[61802053] ; Key Research Program of Frontier Sciences, CAS[QYZDJSSWJSC039] ; Research Program of National Laboratory of Pattern Recognition[Z-2018007]
WOS研究方向Computer Science ; Telecommunications
语种英语
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号WOS:000591817700007
资助机构National Natural Science Foundation of China ; Key Research Program of Frontier Sciences, CAS ; Research Program of National Laboratory of Pattern Recognition
源URL[http://ir.ia.ac.cn/handle/173211/42526]  
专题自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
通讯作者Xu, Changsheng
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Univ Sci & Technol China, Sch Informat Sci & Technol, Dept Automat, Hefei 230052, Peoples R China
3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
4.Peng Cheng Lab, Shenzhen 518066, Peoples R China
推荐引用方式
GB/T 7714		 Ma, Xinhong,Zhang, Tianzhu,Xu, Changsheng. Multi-Level Correlation Adversarial Hashing for Cross-Modal Retrieval[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2020,22(12):3101-3114.
APA Ma, Xinhong,Zhang, Tianzhu,&Xu, Changsheng.(2020).Multi-Level Correlation Adversarial Hashing for Cross-Modal Retrieval.IEEE TRANSACTIONS ON MULTIMEDIA,22(12),3101-3114.
MLA Ma, Xinhong,et al."Multi-Level Correlation Adversarial Hashing for Cross-Modal Retrieval".IEEE TRANSACTIONS ON MULTIMEDIA 22.12(2020):3101-3114.

入库方式： OAI收割

来源：自动化研究所

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。