This paper studies automatic segmentation of multiple
motions from tracked feature points through spectral embedding
and clustering of linear subspaces. We show that
the dimensi...
We present a method for merging multiple partitions into a single partition, by minimising the ratio of pairwise agreements and contradictions between the equivalence relations cor...
We present an approach for recognizing human walking movements using low-level motion regularities and constraints. Biomechanical features for classification are automatically ext...
Tongue Ultrasound imaging is widely used for human speech production analysis and modeling. In this paper, we propose a novel method to automatically detect and track the tongue c...
Our featured wand, automatically tracked by video cameras, provides an inexpensive and natural way for users to input 3D data or interact with devices such as large displays. The ...