We present an algorithm, Hierarchical ISOmetric SelfOrganizing Map (H-ISOSOM), for a concise, organized manifold representation of complex, non-linear, large scale, high-dimension...
—We present in this paper an integrated solution to rapidly recognizing dynamic objects in surveillance videos by exploring various contextual information. This solution consists...
Xiaobai Liu, Liang Lin, Shuicheng Yan, Hai Jin, We...
Characteristics of the 2D shape deformation in human motion contain rich information for human identification and pose estimation. In this paper, we introduce a framework for sim...
Abstract. In this paper, we present a novel graph, sub-graph and supergraph based face representation which captures the facial shape changes and deformations caused due to pose ch...
This paper presents a 3D approach to multi-view object class detection. Most existing approaches recognize object classes for a particular viewpoint or combine classifiers for a f...