In this paper we describe a system to reliably localize the position of the speaker’s face and mouth in videophone sequences. A statistical scheme based on a subspace method is p...
We show that histograms of keypoint descriptor distances can make useful features for visual recognition. Descriptor distances are often exhaustively computed between sets of keyp...
Abstract. A popular framework for the interpretation of image sequences is the layers or sprite model, see e.g. [1], [2]. Jojic and Frey [3] provide a generative probabilistic mode...
This paper addresses the 3D tracking of pose and animation of the human face in monocular image sequences using Active Appearance Models. The classical appearancebased tracking su...
This paper presents a framework for data modeling ntic abstraction of image/video data. The framework is based on spatio-temporalinformation associated with salient objects in an ...
Young Francis Day, Serhan Dagtas, Mitsutoshi Iino,...