ML Anthology

Reducing I/O Cost of Similarity Queries by Processing Several at a Time

Wolfgang Müller, Andreas Henrich
CVPR 2004 pp. 142
doi:10.1109/CVPR.2004.429 /cvpr/2004/muller2004cvpr-reducing/

Abstract

Current research on high-dimensional indexing structures for multimedia retrieval is focused on obtaining optimal performance for single k-NN queries. Within this paper, we argue for parallel processing of multiple nearest neighbor queries. This is beneficial when there is heavy load on the server and efficiency is important. We argue that query performance for parallel queries is an important parameter in the evaluation of the usefulness of indexing structures. We show that by processing multiple queries simultaneously we can dramatically reduce the cost of each single query involved. We support these findings via experiments on VA- and inverted VA-files, an improved variant of VA-files.

CVPR Semantic Scholar

Cite

Text

Müller and Henrich. "Reducing I/O Cost of Similarity Queries by Processing Several at a Time." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004. doi:10.1109/CVPR.2004.429

Markdown

[Müller and Henrich. "Reducing I/O Cost of Similarity Queries by Processing Several at a Time." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004.](https://mlanthology.org/cvpr/2004/muller2004cvpr-reducing/) doi:10.1109/CVPR.2004.429

BibTeX

@inproceedings{muller2004cvpr-reducing,
  title     = {{Reducing I/O Cost of Similarity Queries by Processing Several at a Time}},
  author    = {Müller, Wolfgang and Henrich, Andreas},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2004},
  pages     = {142},
  doi       = {10.1109/CVPR.2004.429},
  url       = {https://mlanthology.org/cvpr/2004/muller2004cvpr-reducing/}
}