Towards more precise social image-tag alignment

Authors:
Ning Zhou;Jinye Peng;Xiaoyi Feng;Jianping Fan
Affiliations:
School of Electronics and Information, Northwestern Polytechnical University, Xi'an, P.R. China and Dept. of Computer Science, UNC-Charlotte, Charlotte, NC;School of Electronics and Information, Northwestern Polytechnical University, Xi'an, P.R. China;School of Electronics and Information, Northwestern Polytechnical University, Xi'an, P.R. China;School of Electronics and Information, Northwestern Polytechnical University, Xi'an, P.R. China and Dept. of Computer Science, UNC-Charlotte, Charlotte, NC
Venue:
MMM'11 Proceedings of the 17th international conference on Advances in multimedia modeling - Volume Part II
Year:
2011

Citing 11
Cited 0

To search or to label?: predicting the performance of search-based automatic image classifiers

MIR '06 Proceedings of the 8th ACM international workshop on Multimedia information retrieval
Why we tag: motivations for annotation in mobile and online media

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Video search reranking through random walk over document-level context graph

Proceedings of the 15th international conference on Multimedia
Image retrieval: Ideas, influences, and trends of the new age

ACM Computing Surveys (CSUR)
Flickr tag recommendation based on collective knowledge

Proceedings of the 17th international conference on World Wide Web
Modeling video hyperlinks with hypergraph for web video reranking

MM '08 Proceedings of the 16th ACM international conference on Multimedia
Tag ranking

Proceedings of the 18th international conference on World wide web
Leveraging large-scale weakly-tagged images to train inter-related classifiers for multi-label annotation

LS-MMRM '09 Proceedings of the First ACM workshop on Large-scale multimedia retrieval and mining
Integrating visual and semantic contexts for topic network generation and word sense disambiguation

Proceedings of the ACM International Conference on Image and Video Retrieval
Retagging social images based on visual and semantic consistency

Proceedings of the 19th international conference on World wide web
Integrating Concept Ontology and Multitask Learning to Achieve More Effective Classifier Training for Multilevel Image Annotation

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Large-scale user contributed images with tags are increasingly available on the Internet. However, the uncertainty of the relatedness between the images and the tags prohibit them from being precisely accessible to the public and being leveraged for computer vision tasks. In this paper, a novel algorithm is proposed to better align the images with the social tags. First, image clustering is performed to group the images into a set of image clusters based on their visual similarity contexts. By clustering images into different groups, the uncertainty of the relatedness between images and tags can be significantly reduced. Second, random walk is adopted to re-rank the tags based on a cross-modal tag correlation network which harnesses both image visual similarity contexts and tag co-occurrences. We have evaluated the proposed algorithm on a large-scale Flickr data set and achieved very positive results.