Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ACCESS.2019.2941542 | IEEE ACCESS |
Keywords | DocType | Volume |
Deep matrix factorization,image annotation,label correlation,multi-view data,machine learning | Journal | 7 |
ISSN | Citations | PageRank |
2169-3536 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhe Xue | 1 | 72 | 14.60 |
Junping Du | 2 | 789 | 91.80 |
Min Zuo | 3 | 0 | 0.68 |
Guorong Li | 4 | 196 | 19.93 |
Qingming Huang | 5 | 3919 | 267.71 |