1. Visual information retrieval using deep learning with visual attention model
Authors : Venkata Ramana Thaduri, K. Venu Gopal Rao
Pages : 280-282
DOI : http://dx.doi.org/10.21172/1.73.040
Keywords : Visual Information RetrievalDeep LearningSaliency modelVisual attentionCBIR Abstract :Abstract. In to-days world there is a huge growth of visual data. These data is increasing beyond the capacity of human brain. All the existing concepts like CBIR, Image Retrieval models are not meeting the current requirements. To overcome these difficulties in the field of visual information retrieval, we are proposing the solution by constructing “visual attention model†by taking the saliency features of the object. To implement this concept and to have the high accuracy and to improve the retrieval efficiency, we are implementing the Deep learning features in our work. Deep learning makes our work simple in moving further to achieve the result set. This paper discusses about the construction of visual attention model, Salience features, Deep learning and the proposed architecture which will be implemented in achieving high accuracy when compared to existing models.
Citing this Journal Article :Venkata Ramana Thaduri, K. Venu Gopal Rao, "Visual information retrieval using deep learning with visual attention model", Summer Special Issue - - June 2016, 280-282
Click here to Submit Copyright Takedown Notice for this article.