Top-down visual saliency facilities object localization by providing a discriminative representation of target objects and a probability map for reducing the search space. In this...
The notion of using context information for solving high-level vision and medical image segmentation problems has been increasingly realized in the field. However, how to learn a...
Conditional Random Fields (CRFs) have proven to perform well on natural language processing tasks like name transliteration, concept tagging or grapheme-to-phoneme (g2p) conversio...
Spectral clustering and eigenvector-based methods have become increasingly popular in segmentation and recognition. Although the choice of the pairwise similarity metric (or affin...
Abstract-Unstructured text represents a large fraction of the world's data. It often contain snippets of structured information within them (e.g., people's names and zip ...
Daisy Zhe Wang, Eirinaios Michelakis, Joseph M. He...