A Novel Image Tag Completion Method Based on Convolutional Neural Transformation
KAUST DepartmentMaterial Science and Engineering Program
Physical Science and Engineering (PSE) Division
Online Publication Date2017-10-25
Print Publication Date2017
Permanent link to this recordhttp://hdl.handle.net/10754/626775
MetadataShow full item record
AbstractIn the problems of image retrieval and annotation, complete textual tag lists of images play critical roles. However, in real-world applications, the image tags are usually incomplete, thus it is important to learn the complete tags for images. In this paper, we study the problem of image tag complete and proposed a novel method for this problem based on a popular image representation method, convolutional neural network (CNN). The method estimates the complete tags from the convolutional filtering outputs of images based on a linear predictor. The CNN parameters, linear predictor, and the complete tags are learned jointly by our method. We build a minimization problem to encourage the consistency between the complete tags and the available incomplete tags, reduce the estimation error, and reduce the model complexity. An iterative algorithm is developed to solve the minimization problem. Experiments over benchmark image data sets show its effectiveness.
CitationGeng Y, Zhang G, Li W, Gu Y, Liang R-Z, et al. (2017) A Novel Image Tag Completion Method Based on Convolutional Neural Transformation. Lecture Notes in Computer Science: 539–546. Available: http://dx.doi.org/10.1007/978-3-319-68612-7_61.
Conference/Event name26th International Conference on Artificial Neural Networks, ICANN 2017