Presentation 2000/7/21
Efficient Retrieval of Multimedia Information with Estimating the Significance of Nearest Neighbors
Norio Katayama, Shin'ichi Satoh,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Nearest-neighbor(NN) search in high-dimensional space is widely used for the similarity retrieval of multimedia information. Recent research results in the literature reveal that NN-search might return insignificant NNs in high-dimensional space. Insignificant NNs are troublesome with respect to the efficiency of the similarity retrieval. Hence, we devised a way to estimate the significance of NNs based on the local intrinsic dimensionality. Then, with applying it, we developed a new NN-search algorithm: the significance-sensitive nearest-neighbor search. This algorithm not only enables us to distinguish more significant NNs from less significant ones but also enables us to cut down the search cost compared with the conventional NN-search algorithm.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Significance of Nearest Neighbors / Multimedia Information / Similarity Retrieval / Nearest Neighbor Search
Paper # DE2000-83
Date of Issue

Conference Information
Committee DE
Conference Date 2000/7/21(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Data Engineering (DE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Efficient Retrieval of Multimedia Information with Estimating the Significance of Nearest Neighbors
Sub Title (in English)
Keyword(1) Significance of Nearest Neighbors
Keyword(2) Multimedia Information
Keyword(3) Similarity Retrieval
Keyword(4) Nearest Neighbor Search
1st Author's Name Norio Katayama
1st Author's Affiliation National Institute of Informatics()
2nd Author's Name Shin'ichi Satoh
2nd Author's Affiliation National Institute of Informatics
Date 2000/7/21
Paper # DE2000-83
Volume (vol) vol.100
Number (no) 228
Page pp.pp.-
#Pages 8
Date of Issue