IJCTT-International Journal of Computer Trends and Technology
Large-scale user contributed images with tags are easily available on photo sharing sites. However, the disturbance or in-appropriate correspondence between the images and tags prohibits them from being leveraged for precise image retrieval and efficient management. To resolve the tag refinement problem, the authors proposing a Ranking method based and Multi-correlation Tensor Factorization (RMTF), to jointly model the ternary relations in-between users, image-tag, and next importantly rebuild the personalized image-tag associations as result. The user interest or background can be explored to eliminate the ambiguity of image tags so, the proposing RMTF is trusted to be guidelines to the formal solutions, which focus only on the binary format type image and tag correlation.