Compact Descriptors for Visual Search (CDVS) Patches Dataset
Abstract/Contents
- Abstract
- MPEG is currently developing a standard titled Compact Descriptors for Visual Search (CDVS) 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 data set of matching pairs of image patches from the MPEG-CDVS image-level data sets.
Description
Type of resource | software, multimedia |
---|---|
Date created | [ca. May 2014] |
Creators/Contributors
Author | Chandrasekhar, Vijay | |
---|---|---|
Author | Takacs, Gabriel | |
Author | Chen, David | |
Author | Tsai, Sam | |
Author | Makar, Mina | |
Author | Girod, Bernd |
Subjects
Subject | mobile visual search |
---|---|
Subject | image patches |
Subject | feature compression |
Genre | Dataset |
Bibliographic information
Related Publication | 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. http://dx.doi.org/10.1109/DCC.2014.50 |
---|---|
Location | https://purl.stanford.edu/js533sk1281 |
Access conditions
- Use and reproduction
- User agrees that, where applicable, content will not be used to identify or to otherwise infringe the privacy or confidentiality rights of individuals. Content distributed via the Stanford Digital Repository may be subject to additional license and use restrictions applied by the depositor.
Preferred citation
- Preferred Citation
- Chandrasekhar, Vijay and Takacs, Gabriel and Chen, David and Tsai, Sam and Makar, Mina and Girod, Bernd. (2014). Compact Descriptors for Visual Search (CDVS) Patches Dataset. Stanford Digital Repository. Available at: http://purl.stanford.edu/js533sk1281
Collection
Research Datasets for MPEG
View other items in this collection in SearchWorksContact information
- Contact
- vijay.cmu@gmail.com
Also listed in
Loading usage metrics...