INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
Image re ranking is effective for improving the performance of a text-based image search. However, existing re ranking algorithms are limited for two main reasons: 1) the textual meta-data associated with images is often mismatched with their actual visual content and 2) the extracted visual features do not accurately describe the semantic similarities between images. Recently, user click information has been used in image re ranking, because clicks have been shown to more accurately describe the relevance of retrieved images to search queries. A significant difficulty for click-based method is the be short of of click data, since only a small number of web images have actually been clicked on by users. In this paper propose a multimodal hyper graph learning-based sparse coding method for image click prediction, and apply the obtained click data to the re ranking of images. We adopt a hyper graph to build a group of manifolds, which explore the complementarily of different features through a group of weights. Unlike a graph that has an edge between two vertices, a hyper edge in a hyper graph connects a set of vertices, and helps preserve the local smoothness of the constructed sparse codes. An irregular optimization process is then performed, and the weights of different modalities and the sparse codes are simultaneously obtained. A voting approach is used to describe the predicted click as a binary event (click or no click), from the images’ corresponding sparse codes. Thorough empirical studies on a large-scale database including nearly unlimited images demonstrate the effectiveness of our approach for click prediction when compared with several other methods.
Keywords:
Social Media, Tag-based Image Retrieval, Topic Community, Image search, Re-ranking.
Cite Article:
"IMAGE RE-RANKING BASED ON TOPIC DIVERSITY", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.5, Issue 7, page no.61 - 68, July-2020, Available :http://www.ijsdr.org/papers/IJSDR2007005.pdf
Downloads:
000336256
Publication Details:
Published Paper ID: IJSDR2007005
Registration ID:192081
Published In: Volume 5 Issue 7, July-2020
DOI (Digital Object Identifier):
Page No: 61 - 68
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn