Cross-Modal Subspace Learning via Pairwise Constraints | |
Ran He(赫然)1![]() ![]() ![]() ![]() | |
发表期刊 | IEEE TRANSACTIONS ON IMAGE PROCESSING
![]() |
2015-12-01 | |
卷号 | 24期号:12页码:5543-5556 |
文章类型 | Article |
摘要 | In multimedia applications, the text and image components in a web document form a pairwise constraint that potentially indicates the same semantic concept. This paper studies cross-modal learning via the pairwise constraint and aims to find the common structure hidden in different modalities. We first propose a compound regularization framework to address the pairwise constraint, which can be used as a general platform for developing cross-modal algorithms. For unsupervised learning, we propose a multi-modal subspace clustering method to learn a common structure for different modalities. For supervised learning, to reduce the semantic gap and the outliers in pairwise constraints, we propose a cross-modal matching method based on compound l(21) regularization. Extensive experiments demonstrate the benefits of joint text and image modeling with semantically induced pairwise constraints, and they show that the proposed cross-modal methods can further reduce the semantic gap between different modalities and improve the clustering/matching accuracy. |
关键词 | Multi Modal Pairwise Constraint Subspace Clustering |
WOS标题词 | Science & Technology ; Technology |
DOI | 10.1109/TIP.2015.2466106 |
关键词[WOS] | DIMENSIONALITY REDUCTION ; MULTIVIEW DATA ; IMAGE ; FRAMEWORK ; FUSION ; STYLE ; RANK |
收录类别 | SCI |
语种 | 英语 |
项目资助者 | National Natural Science Foundation of China(61135002 ; National Basic Research Program of China(2012CB316300) ; 61473289) |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000363251800008 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/10492 |
专题 | 模式识别实验室 |
通讯作者 | Ji, Ye |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Shandong Univ, Dept Control Sci & Engn, Jinan 250100, Peoples R China |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Ran He,Man Zhang,Liang Wang,et al. Cross-Modal Subspace Learning via Pairwise Constraints[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2015,24(12):5543-5556. |
APA | Ran He,Man Zhang,Liang Wang,Ye Ji,Qiyue Yin,&Ji, Ye.(2015).Cross-Modal Subspace Learning via Pairwise Constraints.IEEE TRANSACTIONS ON IMAGE PROCESSING,24(12),5543-5556. |
MLA | Ran He,et al."Cross-Modal Subspace Learning via Pairwise Constraints".IEEE TRANSACTIONS ON IMAGE PROCESSING 24.12(2015):5543-5556. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Cross-Modal Subspace(2205KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论