Label Correlation Guided Deep Multi-View Image Annotation
Automatic image annotation is an important technique which has been widely applied in many fields such as social network image analysis and retrieval, face recognition and so on. Multi-view image annotation aims to utilize multi-view complementary information to achieve more effective annotation res...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8839057/ |
| _version_ | 1818949175062036480 |
|---|---|
| author | Zhe Xue Junping Du Min Zuo Guorong Li Qingming Huang |
| author_facet | Zhe Xue Junping Du Min Zuo Guorong Li Qingming Huang |
| author_sort | Zhe Xue |
| collection | DOAJ |
| description | Automatic image annotation is an important technique which has been widely applied in many fields such as social network image analysis and retrieval, face recognition and so on. Multi-view image annotation aims to utilize multi-view complementary information to achieve more effective annotation results. However, the existing multi-view image annotation methods cannot well handle the complex and diversified multi-view feature, and the label correlation is also ignored. In this paper, we propose an image annotation method by integrating deep multi-view latent space learning and label correlation guided image annotation into a unified framework, which is termed as Label Correlation guided Deep Multi-view image annotation (LCDM) method. LCDM first learns a consistent multi-view representation via deep matrix factorization, which well captures multi-view complementary information. Then, label correlation is exploited to improve the discriminating power of the classifiers. We propose a unified objective function so that multi-view data representation and classifiers can be jointly learned. Extensive experimental results on various image datasets demonstrate the effectiveness of our method. |
| first_indexed | 2024-12-20T08:58:31Z |
| format | Article |
| id | doaj.art-d10b1445d14d4ffda346283f7fe07d86 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T08:58:31Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-d10b1445d14d4ffda346283f7fe07d862022-12-21T19:45:56ZengIEEEIEEE Access2169-35362019-01-01713470713471710.1109/ACCESS.2019.29415428839057Label Correlation Guided Deep Multi-View Image AnnotationZhe Xue0https://orcid.org/0000-0001-6123-0043Junping Du1Min Zuo2Guorong Li3Qingming Huang4Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia, School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, ChinaBeijing Key Laboratory of Intelligent Telecommunication Software and Multimedia, School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, ChinaNational Engineering Laboratory for Agri-product Quality Traceability, Beijing Technology and Business University, Beijing, ChinaSchool of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, ChinaSchool of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, ChinaAutomatic image annotation is an important technique which has been widely applied in many fields such as social network image analysis and retrieval, face recognition and so on. Multi-view image annotation aims to utilize multi-view complementary information to achieve more effective annotation results. However, the existing multi-view image annotation methods cannot well handle the complex and diversified multi-view feature, and the label correlation is also ignored. In this paper, we propose an image annotation method by integrating deep multi-view latent space learning and label correlation guided image annotation into a unified framework, which is termed as Label Correlation guided Deep Multi-view image annotation (LCDM) method. LCDM first learns a consistent multi-view representation via deep matrix factorization, which well captures multi-view complementary information. Then, label correlation is exploited to improve the discriminating power of the classifiers. We propose a unified objective function so that multi-view data representation and classifiers can be jointly learned. Extensive experimental results on various image datasets demonstrate the effectiveness of our method.https://ieeexplore.ieee.org/document/8839057/Deep matrix factorizationimage annotationlabel correlationmulti-view datamachine learning |
| spellingShingle | Zhe Xue Junping Du Min Zuo Guorong Li Qingming Huang Label Correlation Guided Deep Multi-View Image Annotation IEEE Access Deep matrix factorization image annotation label correlation multi-view data machine learning |
| title | Label Correlation Guided Deep Multi-View Image Annotation |
| title_full | Label Correlation Guided Deep Multi-View Image Annotation |
| title_fullStr | Label Correlation Guided Deep Multi-View Image Annotation |
| title_full_unstemmed | Label Correlation Guided Deep Multi-View Image Annotation |
| title_short | Label Correlation Guided Deep Multi-View Image Annotation |
| title_sort | label correlation guided deep multi view image annotation |
| topic | Deep matrix factorization image annotation label correlation multi-view data machine learning |
| url | https://ieeexplore.ieee.org/document/8839057/ |
| work_keys_str_mv | AT zhexue labelcorrelationguideddeepmultiviewimageannotation AT junpingdu labelcorrelationguideddeepmultiviewimageannotation AT minzuo labelcorrelationguideddeepmultiviewimageannotation AT guorongli labelcorrelationguideddeepmultiviewimageannotation AT qingminghuang labelcorrelationguideddeepmultiviewimageannotation |