With the availability of massive amounts of digital images in personal and on-line collections, effective techniques for navigating, indexing and searching images become more crucial. In this thesis, we rely on the image visual content as the main source of information to represent images. Starting from the bag of visual words (BOW) representation, a higher-level visual representation is learned where each image is modeled as a mixture of visual topics depicted in the image and related to high-level topics. First, we enhance the BOW representation by characterizing the spatial-color constitution of an image with a mixture of n Gaussians in the feature space. This leads to propose a novel descriptor, the Edge Context, which plays a role as a...
Finding relations between image semantics and image characteristics is a problem of long standing in...
Bag-of-visual Words (BoW) image representation is getting popular in computer vision and multimedia ...
International audienceThis paper proposes to investigate the potential benefit of the use of low-lev...
With the availability of massive amounts of digital images in personal and on-line collections, effe...
International audienceWith the availability of massive amounts of digital images in personal and on-...
International audienceWith the availability of massive amounts of digital images in personal and on-...
Avec l'augmentation exponentielle de nombre d'images disponibles sur Internet, le besoin en outils e...
International audienceHaving effective methods to access the desired images is essential nowadays wi...
International audienceHaving effective methods to access the desired images is essential nowadays wi...
International audienceHaving effective methods to access the desired images is essential nowadays wi...
Visual Category Recognition aims at fast classification of objects, as well as scenery, action, and ...
A novel image representation, termed semantic image representation, that incorporates contextual inf...
In large social networks, web objects become increasingly popular. Multimedia object classification ...
A novel image representation, termed semantic image representation, that incorporates contextual inf...
A l'ère d'Internet, la classification informatisée des images est d'une importance cruciale pour l’u...
Finding relations between image semantics and image characteristics is a problem of long standing in...
Bag-of-visual Words (BoW) image representation is getting popular in computer vision and multimedia ...
International audienceThis paper proposes to investigate the potential benefit of the use of low-lev...
With the availability of massive amounts of digital images in personal and on-line collections, effe...
International audienceWith the availability of massive amounts of digital images in personal and on-...
International audienceWith the availability of massive amounts of digital images in personal and on-...
Avec l'augmentation exponentielle de nombre d'images disponibles sur Internet, le besoin en outils e...
International audienceHaving effective methods to access the desired images is essential nowadays wi...
International audienceHaving effective methods to access the desired images is essential nowadays wi...
International audienceHaving effective methods to access the desired images is essential nowadays wi...
Visual Category Recognition aims at fast classification of objects, as well as scenery, action, and ...
A novel image representation, termed semantic image representation, that incorporates contextual inf...
In large social networks, web objects become increasingly popular. Multimedia object classification ...
A novel image representation, termed semantic image representation, that incorporates contextual inf...
A l'ère d'Internet, la classification informatisée des images est d'une importance cruciale pour l’u...
Finding relations between image semantics and image characteristics is a problem of long standing in...
Bag-of-visual Words (BoW) image representation is getting popular in computer vision and multimedia ...
International audienceThis paper proposes to investigate the potential benefit of the use of low-lev...