Abstract. This paper explores the use of deformable mesh for registration of microscopic iris image sequences. The registration, as an effort for stabilizing and rectifying images ...
Xubo B. Song, Andriy Myronenko, Stephen R. Plank, ...
Training principles for unsupervised learning are often derived from motivations that appear to be independent of supervised learning. In this paper we present a simple unificatio...
Tensors are nowadays an increasing research domain in different areas, especially in image processing, motivated for example by DT-MRI (Diffusion Tensor Magnetic Resonance Imaging...
We present SchemaScope, a system to derive Document Type Definitions and XML Schemas from corpora of sample XML documents. Tools are provided to visualize, clean, and refine exist...
HMF is a conservative extension of Hindley-Milner type inference with first-class polymorphism. In contrast to other proposals, HML uses regular System F types and has a simple ty...