Multi-Illuminant estimation
We propose CRF based method for multi-illuminant estimation. In addition we propose a data set with pixelwise ground-truth of both real scenes and laboratroy setting images.

Discriminative Color Descriptors
In this work we propose a number of discriminative color descriptors which are optimizing the discriminative power with respect to a classifciation problem. In addition, we propose a set of universal color descriptors which can be used without any prior training on any data set.

Synthetic image intrinsic image data set
We propose a synthetic image data set for intrinsic image evaluation.

Action Recognition in Still Images
We evaluate the usagge of color for action recognition in still images.

Color object detection
We extend part-based object detection with color information. Results on VOC PASCAL are provided and code is available.

Compact multi-cue vocabularies
We propose a novel approach for constructing multi-cue Portmanteau vocabularies for image classification.

Object Recoloring based on Intrinsic Image Estimation
In this research we decompose the image into its intrinsic reflectance components with the aim to recolor scenes.

Color Constancy
On this website links to color constancy research, available code, and data bases can be found.

Discriminative Pyramids for Object and Scene Recognition (+code)
In this research we address the high dimenssionality of spatial pyramids, which is generally considered to be its most serious disadvantage.

Physics-based color image segmentation (+code)
Based on an analysis of the bi-directional reflection model we propose a method which is particularly suited for segmentation in the presence of shadow and highlight edges.

Color attention for object recognition (+code)
We propose a novel image representation where color attention is used to sample the shape description of the image.

Color Feature Detection for Object Recognition (+code)
Luminance edges are still the main source of information in the state-of-the-art methods for feature detection. We propose to exploit the statistical structure of luminance and color in natural images to extract the most discriminative features from the viewpoint of information theory for object recognition.

VOC PASCAL 2009 image classification challenge
The CVC obtained the second position in the classification challenge, and obtained the best score on 2 out of the 20 classes.

VOC PASCAL 2009 image segmentation challenge
The CVC obtained the second position in the segmenation challenge, winning 6 out of 20 classes.