This paper presents a robust and accurate method for joint head pose and facial actions tracking, even under challenging conditions such as varying lighting, large head movements,...
Stereo is a useful technique for obtaining depth information from images. However, it is required that the baseline length between two cameras should be large to increase depth pr...
Complex 3D interaction tasks require the manipulation of a large number of input parameters. Spatial input devices can be constructed such that their structure reflects the task ...
Semistructured data is not strictly typed like relational or object-oriented data and may be irregular or incomplete. It often arises in practice, e.g., when heterogeneous data so...
Serge Abiteboul, Jason McHugh, Michael Rys, Vasili...
Abstract. We propose a hierarchical process for inferring the 3D pose of a person from monocular images. First we infer a learned view-based 2D body model from a single image using...