We address the problem of extracting bilingual chunk pairs from parallel text to create training sets for statistical machine translation. We formulate the problem in terms of a s...
Hierarchical conditional random fields have been successfully applied to object segmentation. One reason is their ability to incorporate contextual information at different scales....
Xavier Boix, Josep M. Gonfaus, Joost van de Weijer...
Combining information from the higher level and the lower level has long been recognized as an essential component in holistic image understanding. However, an efficient inferenc...
A problem of using mixture-of-Gaussian models for unsupervised texturesegmentationisthat "multimodal"textures(such ascan often be encountered in natural images) cannot b...
In order to build a simulated robot that accepts instructions in unconstrained natural language, a corpus of 427 route instructions was collected from human subjects in the office...