Foundations and Trends in Information Retrieval
Image categorization combining neighborhood methods and boosting
LS-MMRM '09 Proceedings of the First ACM workshop on Large-scale multimedia retrieval and mining
Learning social tag relevance by neighbor voting
IEEE Transactions on Multimedia
Nonnegative shared subspace learning and its application to social media retrieval
Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining
Innovative directions in self-organized distributed multimedia systems
Multimedia Tools and Applications
Lookapp: interactive construction of web-based concept detectors
Proceedings of the 1st ACM International Conference on Multimedia Retrieval
MM '11 Proceedings of the 19th ACM international conference on Multimedia
Improving image tags by exploiting web search results
Multimedia Tools and Applications
Topic based photo set retrieval using user annotated tags
Multimedia Tools and Applications
Learning to Recommend Descriptive Tags for Questions in Social Forums
ACM Transactions on Information Systems (TOIS)
Journal of Visual Communication and Image Representation
Hi-index | 0.00 |
Automatic image tagging is important yet challenging due to the semantic gap and the lack of learning examples to model a tag's visual diversity. Meanwhile, social user tagging is creating rich multimedia content on the web. In this paper, we propose to combine the two tagging approaches in a search-based framework. For an unlabeled image, we first retrieve its visual neighbors from a large user-tagged image database. We then select relevant tags from the result images to annotate the unlabeled image. To tackle the unreliability and sparsity of user tagging, we introduce a joint-modality tag relevance estimation method which efficiently addresses both textual and visual clues. Experiments on 1.5 million Flickr photos and 10 000 Corel images verify the proposed method.