Add to ORKGThis paper proposes a new approach to learning a discriminative model of object classes, incorporating appearance, shape and context information efficiently. The learned model is used for automatic visual recognition and semantic segmentation of photographs. Our discriminative model exploits novel features, based on textons, which jointly model shape and texture. Unary classification and feature selection is achieved using shared boosting to give an efficient classifier which can be applied to a large number of classes. Accurate image segmentation is achieved by incorporating these classifiers in a conditional random field. Efficient trainin
The recognition of categories of objects in images has become a central topic in computer vision. A...
We present an approach that combines bag-of-words and spatialmodels to perform semantic and syntacti...
We present a new co-clustering problem of images and visual features. The prob-lem involves a set of...
Abstract. This paper proposes a new approach to learning a discriminative model of object classes, i...
This dissertation addresses the task of detecting instances of object categories in photographs. We ...
A key ingredient in the design of visual object classification systems is the identification of rele...
We consider the problem of detecting a large number of different object classes in cluttered scenes....
International audienceThis paper proposes a new algorithm for image recognition, which consists of (...
We present a method to learn object class models from unlabeled and unsegmented cluttered scenes for...
Existing work on multi-class object detection usually does not cover the entire viewsphere of each c...
In this paper, we propose a new scene-based conditional model and investigate its performance on mul...
This paper presents a new model of object classes which incorporates appearance and shape informatio...
We consider the problem of detecting a large number of different classes of objects in cluttered sce...
The concepts of objects and attributes are both impor-tant for describing images precisely, since ve...
This paper proposes a novel approach for multi-view multi-pose object detection using discriminative...
The recognition of categories of objects in images has become a central topic in computer vision. A...
We present an approach that combines bag-of-words and spatialmodels to perform semantic and syntacti...
We present a new co-clustering problem of images and visual features. The prob-lem involves a set of...
Abstract. This paper proposes a new approach to learning a discriminative model of object classes, i...
This dissertation addresses the task of detecting instances of object categories in photographs. We ...
A key ingredient in the design of visual object classification systems is the identification of rele...
We consider the problem of detecting a large number of different object classes in cluttered scenes....
International audienceThis paper proposes a new algorithm for image recognition, which consists of (...
We present a method to learn object class models from unlabeled and unsegmented cluttered scenes for...
Existing work on multi-class object detection usually does not cover the entire viewsphere of each c...
In this paper, we propose a new scene-based conditional model and investigate its performance on mul...
This paper presents a new model of object classes which incorporates appearance and shape informatio...
We consider the problem of detecting a large number of different classes of objects in cluttered sce...
The concepts of objects and attributes are both impor-tant for describing images precisely, since ve...
This paper proposes a novel approach for multi-view multi-pose object detection using discriminative...
The recognition of categories of objects in images has become a central topic in computer vision. A...
We present an approach that combines bag-of-words and spatialmodels to perform semantic and syntacti...
We present a new co-clustering problem of images and visual features. The prob-lem involves a set of...