Human visual recognition is based largely on shape, yet effectively using shapes in natural image retrieval is a challenging task. Most existing methods are based on the geometric...
In this paper, we study the problem of nonnegative graph
embedding, originally investigated in [14] for reaping the
benefits from both nonnegative data factorization and the
spe...
Changhu Wang (University of Science and Technology...
Computer systems increasingly carry out tasks in mixed networks, that is in group settings in which they interact both with other computer systems and with people. Participants in...
Ya'akov Gal, Barbara J. Grosz, Sarit Kraus, Avi Pf...
In this paper, we propose a new transductive learning framework for image retrieval, in which images are taken as vertices in a weighted hypergraph and the task of image search is...
Normalized Cuts has successfully been applied to a wide range of tasks in computer vision, it is indisputably one of the most popular segmentation algorithms in use today. A number...