Compact Descriptors for Visual Search (CDVS) Patches Dataset

<a href="https://embed.stanford.edu/iframe/?url=https%3A%2F%2Fpurl.stanford.edu%2Fjs533sk1281" class="su-underline">Show Content</a>

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.

Type of resource	software, multimedia
Date created	[ca. May 2014]

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

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: 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

Research Datasets for MPEG

Loading usage metrics...