A data set for color research

By Kobus Barnard, Lindsay Martin, Brian V. Funt, Adam Coath. 2002

318 citations recorded by the source corpus.

Subfields: Atomic and Molecular Physics, and Optics, Cognitive Neuroscience, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/58400ccf99214b17c6a9b6d460515293adc88fec

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atomic and Molecular Physics, and Optics

1. Joost van de Weijer
2. Cees G. M. Snoek
3. Cordelia Schmid
4. Brian V. Funt
5. Kobus Barnard
6. Jan-Mark Geusebroek
7. Arnold M. W. Smeulders
8. Jan van Gemert

In Cognitive Neuroscience

1. Joost van de Weijer
2. Cordelia Schmid
3. Arnold M. W. Smeulders

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Cordelia Schmid
3. Andrew Zisserman
4. Xiaogang Wang
5. Jitendra Malik
6. Dacheng Tao
7. Ming-Hsuan Yang
8. Li Fei-Fei

Citations in the corpus

• The Amsterdam Library of Object Images (2004, unknown): “A collection of 20 objects under various illumination sources is presented by Barnard et al. (2002), representing a small but valuable data set to test color constancy algorithms.”
• Coloring Local Feature Extraction (2006, methodology): “It consists of a Mondrian composition captured under 11 different illuminants (the images are from the Simon Frasier data set [ 23 ]).”
• A comparison of computational color constancy algorithms. I: Methodology and experiments with synthesized data (2002, methodology): “more, the methodology used in this work has been informed by our work with a large data set of real images [1], [4].”
• Bayesian color constancy revisited (2008, background): “A further dataset [ 2 ] is available with labelled illuminant, but containing only 30 indoor scenes, under various illuminants, which is useful for testing purposes but not sufficiently diverse for training.”
• Computational Color Constancy: Survey and Experiments (2011, unknown): “The first step toward realistic evaluation of color constancy methods involves isolated compositions of objects that are illuminated by 11 different light sources [122].”
• The challenge problem for automated detection of 101 semantic concepts in multimedia (2006, methodology): “For each experiment, we evaluate generic video indexing perfor­mance on 85 hours of international broadcast news data, from the TRECVID 2005/2006 benchmark, using a lexicon of 101 semantic concepts.”