Paper Info
Title
Improving Web Image Search Results Using Query-Relative Classifiers
Abstract
Web image search using text queries has received considerable attention. However, current state-of-the-art approaches require training models for every new query, and are therefore unsuitable for real-world web search applications. The key contribution of this paper is to introduce generic classifiers that are based on query-relative features which can be used for new queries without additional training. They combine textual features, based on the occurence of query terms in web pages and image meta-data, and visual histogram representations of images. The second contribution of the paper is a new database for the evaluation of web image search algorithms. It includes 71478 images returned by a web search engine for 353 different search queries, along with their meta-data and ground-truth annotations. Using this data set, we compared the image ranking performance of our model with that of the search engine, and with an approach that learns a separate classifier for each query. Our generic models that use query-relative features improve significantly over the raw search engine ranking, and also outperform the query-specific models.
Year
DOI
Venue
2010
10.1109/CVPR.2010.5540092
2010 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
Keywords
Field
DocType
web pages,image classification,histograms,web search engine,image retrieval,ground truth,visualization,search engines,machine vision,graphical models,quantization,search engine,engines
Web search engine,Data mining,Web search query,Metasearch engine,Phrase search,Semantic search,Information retrieval,Query expansion,Computer science,Web query classification,Search analytics
Conference
Volume
Issue
ISSN
2010
1
1063-6919
Citations 
PageRank 
References 
62
2.66
14
Authors
4
Name
Order
Citations
PageRank
Josip Krapac119912.31
Moray Allan228132.18
J. J. Verbeek33944181.44
Frédéric Jurie43924235.82