Classical dynamic Bayesian networks (DBNs) are based on the homogeneous Markov assumption and cannot deal with heterogeneity and non-stationarity in temporal processes. Various ap...
This paper addresses the problem of segmenting a textured mesh into objects or object classes, consistently with user-supplied seeds. We view this task as transductive learning and...
With the goal of supporting the knowledge circulation and creation process in a society, we have studied story-based communication in a network community. On the basis of this res...
Yukiko I. Nakano, Toshihiro Murayama, Masashi Okam...
We present a method for the simultaneous detection and segmentation of people from static images. The proposed technique requires no manual segmentation during training, and explo...
Abstract. Selective attention shift can help neural networks learn invariance. We describe a method that can produce a network with invariance to changes in visual input caused by ...