Download PDFOpen PDF in browser

Web Image Search Re-ranking Dependent on Diversity

EasyChair Preprint no. 2342

4 pagesDate: January 9, 2020


Social media sharing websites sanction users to annotate images with free tags, which significantly contribute to the development of the web image retrieval. Tag-predicated image search is a consequential method to find images shared by users in gregarious networks. However, how to make the top ranked result germane and with diversity is arduous. In this paper, we propose a topic diverse ranking approach for tag-predicated image retrieval with the consideration of promoting the topic coverage performance. First, we construct a tag graph predicated on the homogeneous attribute between each tag. Then community detection technique is led to mine the subject network of each tag. From that point forward, inter network and intra network positioning are acquainted with acquire the last recovered outcomes. In the inter-community ranking process, an adaptive desultory walk model is employed to rank the community predicated on the multi-information of each topic community. Besides, we build an inverted index structure for images to expedite the probing process. Experimental results on Flickr dataset and NUS-Wide datasets show the efficacy of the proposed approach.

Keyphrases: gregarious networks, homogeneous attribute, Tag-predicate

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
  author = {Mohd. Shafi Pathan and Mohd. Basit Ansari},
  title = {Web Image Search Re-ranking Dependent on Diversity},
  howpublished = {EasyChair Preprint no. 2342},

  year = {EasyChair, 2020}}
Download PDFOpen PDF in browser