Dimension-Specific Search for Multimedia Retrieval

Authors:
Zi Huang;Heng Tao Shen;Dawei Song;Xue Li;Stefan Rueger
Affiliations:
School of ITEE, The University of Queensland, Australia;School of ITEE, The University of Queensland, Australia;School of Computing, The Robert Gordon University, UK;School of ITEE, The University of Queensland, Australia;Knowledge Media institute, The Open University, UK
Venue:
DASFAA '09 Proceedings of the 14th International Conference on Database Systems for Advanced Applications
Year:
2009

Citing 7
Cited 0

Searching in high-dimensional spaces: Index structures for improving the performance of multimedia databases

ACM Computing Surveys (CSUR)
Efficient k-NN search on vertically decomposed data

Proceedings of the 2002 ACM SIGMOD international conference on Management of data
M-tree: An Efficient Access Method for Similarity Search in Metric Spaces

VLDB '97 Proceedings of the 23rd International Conference on Very Large Data Bases
A Quantitative Analysis and Performance Study for Similarity-Search Methods in High-Dimensional Spaces

VLDB '98 Proceedings of the 24rd International Conference on Very Large Data Bases
iDistance: An adaptive B+-tree based indexing method for nearest neighbor search

ACM Transactions on Database Systems (TODS)
Approximation Techniques for Indexing the Earth Mover's Distance in Multimedia Databases

ICDE '06 Proceedings of the 22nd International Conference on Data Engineering
Multi-probe LSH: efficient indexing for high-dimensional similarity search

VLDB '07 Proceedings of the 33rd international conference on Very large data bases

Quantified Score

Hi-index	0.00

Visualization

Abstract

Observing that current Global Similarity Measures (GSM) which average the effect of few significant differences on all dimensions may cause possible performance limitation, we propose the first Dimension-specific Similarity Measure (DSM) to take local dimension-specific constraints into consideration. The rationale for DSM is that significant differences on some individual dimensions may lead to different semantics. An efficient search algorithm is proposed to achieve fast Dimension-specific KNN (DKNN) retrieval. Experiment results show that our methods outperform traditional methods by large gaps.