SaveRF: Towards efficient relevance feedback search

Shen, Heng Tao, Ooi, Beng Chin and Tan, Kian-Lee (2006). SaveRF: Towards efficient relevance feedback search. In: Ling Liu, Andreas Reuter, Kyu-Young Whang and Jianjun Zhang, Proceedings of the 22nd International Conference on Data Engineering, ICDE 2006. 22nd International Conference on Data Engineering (ICDE 2006), Atlanta, U.S.A., (1-3). 3-8 April 2006. doi:10.1109/ICDE.2006.132


Author Shen, Heng Tao
Ooi, Beng Chin
Tan, Kian-Lee
Title of paper SaveRF: Towards efficient relevance feedback search
Conference name 22nd International Conference on Data Engineering (ICDE 2006)
Conference location Atlanta, U.S.A.
Conference dates 3-8 April 2006
Proceedings title Proceedings of the 22nd International Conference on Data Engineering, ICDE 2006
Place of Publication Los Alamitos, California, U.S.A.
Publisher IEEE
Publication Year 2006
Sub-type Fully published paper
DOI 10.1109/ICDE.2006.132
ISBN Online proceedings
Editor Ling Liu
Andreas Reuter
Kyu-Young Whang
Jianjun Zhang
Start page 1
End page 3
Total pages 3
Language eng
Abstract/Summary In multimedia retrieval, a query is typically interactively refined towards the ‘optimal’ answers by exploiting user feedback. However, in existing work, in each iteration, the refined query is re-evaluated. This is not only inefficient but fails to exploit the answers that may be common between iterations. In this paper, we introduce a new approach called SaveRF (Save random accesses in Relevance Feedback) for iterative relevance feedback search. SaveRF predicts the potential candidates for the next iteration and maintains this small set for efficient sequential scan. By doing so, repeated candidate accesses can be saved, hence reducing the number of random accesses. In addition, efficient scan on the overlap before the search starts also tightens the search space with smaller pruning radius. We implemented SaveRF and our experimental study on real life data sets show that it can reduce the I/O cost significantly.
Subjects E1
280103 Information Storage, Retrieval and Management
700103 Information processing services
Keyword Multimedia retrieval
Query evaluation
Feedback
SaveRF
Q-Index Code E1
Additional Notes Published as an abstract in print proceedings: ISBN: 0-7695-2570-9, p. 110

 
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Thu, 23 Aug 2007, 22:23:17 EST