Conventional subspace learning or recent feature extraction methods consider globality as the key criterion to design discriminative algorithms for image classification. We demonst...
Yun Fu, Zhu Li, Junsong Yuan, Ying Wu, Thomas S. H...
This paper proposes a new generic object recognition system based on multi-scale affineinvariant image regions. Image segments are obtained by a watershed transform of the princip...
Wei Zhang, Hongli Deng, Thomas G. Dietterich, Eric...
This article proposes a method for learning object templates
composed of local sketches and local textures, and
investigates the relative importance of the sketches and textures
...
Haifeng Gong, Song Chun Zhu, Ying Nian Wu, Zhangzh...
The Prague texture segmentation data-generator and benchmark is a web based (http://mosaic.utia.cas.cz) service designed to mutually compare and rank different texture segmenters,...
Convolution kernels, constructed by convolution of sub-kernels defined on sub-structures of composite objects, are widely used in classification, where one important issue is to ch...