Learning to Rank Images for Complex Queries in Concept-based Search
Cui, C., Shen, J., Chen, Z., Wang, S., & Ma, J. (2018). Learning to Rank Images for Complex Queries in Concept-based Search. Neurocomputing, 274, 19-28. https://doi.org/10.1016/j.neucom.2016.05.118
Published in
NeurocomputingDate
2018Copyright
© 2017 Elsevier B.V. This is a final draft version of an article whose final and definitive form has been published by Elsevier. Published in this repository with the kind permission of the publisher.
Concept-based image search is an emerging search paradigm that utilizes a set of concepts as intermediate semantic descriptors of images to bridge the semantic gap. Typically, a user query is rather complex and cannot be well described using a single concept. However, it is less effective to tackle such complex queries by simply aggregating the individual search results for the constituent concepts. In this paper, we propose to introduce the learning to rank techniques to concept-based image search for complex queries. With freely available social tagged images, we first build concept detectors by jointly leveraging the heterogeneous visual features. Then, to formulate the image relevance, we explicitly model the individual weight of each constituent concept in a complex query. The dependence among constituent concepts, as well as the relatedness between query and non-query concepts, are also considered through modeling the pairwise concept correlations in a factorization way. Finally, we train our model to directly optimize the image ranking performance for complex queries under a pairwise learning to rank framework. Extensive experiments on two benchmark datasets well verified the promise of our approach.
...
Publisher
Elsevier BVISSN Search the Publication Forum
0925-2312Keywords
Publication in research information system
https://converis.jyu.fi/converis/portal/detail/Publication/26949709
Metadata
Show full item recordCollections
Related items
Showing items with similar title or keywords.
-
Behavior-based personalization in web search
Cai, Fei; Wang, Shuaiqiang; de Rijke, Maarten (Wiley, 2017)Personalized search approaches tailor search results to users' current interests, so as to help improve the likelihood of a user finding relevant documents for their query. Previous work on personalized search focuses on ... -
Sixth graders’ evaluation strategies when reading Internet search results : an eye-tracking study
Hautala, Jarkko; Kiili, Carita; Kammerer, Yvonne; Loberg, Otto; Hokkanen, Sanna; Leppänen, Paavo H.T. (Taylor and Francis, 2018)Eye-tracking technology was used to examine Internet search result evaluation strategies adopted by sixth-grade students (N = 36) during ten experimental information search tasks. The relevancy of the search result’s title, ... -
User Session Level Diverse Reranking of Search Results
Ren, Pengjie; Chen, Zhumin; Ma, Jun; Wang, Shuaiqiang; Zhang, Zhiwei; Ren, Zhaochun; Ma, Tinghuai (Elsevier BV, 2018)Most Web search diversity approaches can be categorized as Document Level Diversification (DocLD), Topic Level Diversification (TopicLD) or Term Level Diversification (TermLD). DocLD selects the relevant documents with ... -
Improving search engine results using different machine learning models and tools
Ambaye, Michael (2020)The aim of this thesis is to provide viable methods that can be used to improve the return position (RP) of a relevant document when a natural language query (NLQ) is applied by a user. For the purpose of demonstration, ... -
Challenges and insights in semantic search using language models
Hajihashemi Varnousfaderani, Elahe (2023)Information Retrieval systems such as search engines, originally designed to assist users in finding information, have evolved to become more potent and have found utility in wider range of applications by incorporating ...