Title :
Predicting the effectiveness of queries for visual search
Author :
Bing Li ; Ling-Yu Duan ; Yiming Chen ; Rongrong Ji ; Wen Gao
Author_Institution :
Inst. of Comput. Technol., Beijing, China
Abstract :
Poor retrieval performance significantly degenerates users´ experience of visual search, especially in mobile search. Ideally, users would like to be alerted when bad queries are present, which helps eliminate latency as well as waste of bandwidth, especially in 3G wireless environment. In this paper, we propose a visual query performance prediction (v-QPP) approach to predict the retrieval effectiveness. We employ latent dirichlet allocation (LDA)to derive latent topics from image database. From the collection statistics, we model the query´s specificity based on topics. High specificity helps a retrieval system to derive user´s search intent exactly. Moreover, as low discriminative content is difficult to search in terms of distinguishing relevant images from irrelevant one, we propose a topics based inverse concept frequency (t-ICF) model to deal with specific queries but difficult to discriminate in the reference database. Comparison experiments over MPEG CDVS benchmarking datasets have shown our method significantly outperforms existing approaches in document retrieval.
Keywords :
3G mobile communication; image retrieval; statistical analysis; visual databases; 3G wireless environment; LDA; collection statistics; image database; latent Dirichlet allocation; latent topic; mobile search; query specificity; retrieval effectiveness; retrieval performance; retrieval system; t-ICF model; topics based inverse concept frequency; user search; v-QPP approach; visual query performance prediction; visual search; Atmospheric modeling; Correlation; Databases; Mobile communication; Resource management; Semantics; Visualization; mobile; query performance prediction; topic model; visual search;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on
Conference_Location :
Kyoto
Print_ISBN :
978-1-4673-0045-2
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2012.6288389