In this paper we introduce a novel approach to single view reconstruction using shape grammars. Our approach consists in modeling architectural styles using a set of basic shapes ...
In this paper, we propose a group-sensitive multiple kernel learning (GS-MKL) method to accommodate the intra-class diversity and the inter-class correlation for object categoriza...
Effective and efficient navigation and representation of the entire structure of the product catalogue is one of the important factors for on-line market. This paper proposes an a...
Mao Lin Huang, Quang Vinh Nguyen, Viet Cuong Vo, J...
Abstract-In this paper, we construct a neural-inspired computational model based on the representational capabilities of receptive fields. The proposed model, known as Shape Encodi...
In this paper, based on manifold harmonics, we propose a novel framework for 3D shape similarity comparison and partial matching. First, we propose a novel symmetric meanvalue rep...
Huai-Yu Wu, Hongbin Zha, Tao Luo, Xulei Wang, Song...