Yet Another Computer Vision Index To Datasets (YACVID) - Details

Stand: 2017-09-21 000000m 01:38:39 - Overview

Attribute Current Content New
Name (Institute + Shorttitle)Visual Search Patches 
Description (include details on usage, files and paper references)The Compact Descriptors for Visual Search Patches Dataset (CDVS) is a dataset comprised of pairwise image patches. MPEG is a standard titled Compact Descriptors for Visual Search for descriptor extraction and compression. In this work, we develop comprehensive patch-level experiments for a direct comparison of low bitrate descriptors for visual search. For evaluating different compression schemes, we propose a dataset of matching pairs of image patches from the MPEG-CDVS image-level datasets.

Institute for Infocomm Research: V. Chandrasekhar
Microsoft: G. Takacs
Stanford: D. Chen, S. Tsai, B. Girod
Qualcomm: M. Makar

V. Chandrasekhar, G. Takacs, D. Chen, S. Tsai, M. Makar, and B. Girod, Feature matching performance of compact descriptors for visual search, IEEE Data Compression Conference (DCC), March 2014.
URL Link 
Files (#)
References (SKIPPED)
Category (SKIPPED) 
Tags (single words, spaced)patch matching retrieval descriptor feature mpeg 
Last Changed2017-09-21 
Turing (2.12+3.25=?) :-)