Sciweavers

376 search results - page 52 / 76
» On the Use of Virtual Evidence in Conditional Random Fields
Sort
View
ICCV
2009
IEEE
15 years 1 months ago
Piecewise Planar Stereo for Image-based Rendering
We present a novel multi-view stereo method designed for image-based rendering that generates piecewise planar depth maps from an unordered collection of photographs. First a di...
Sudipta N. Sinha, Drew Steedly and Richard Szelisk...
ICCV
2007
IEEE
14 years 10 months ago
Objects in Context
In the task of visual object categorization, semantic context can play the very important role of reducing ambiguity in objects' visual appearance. In this work we propose to...
Andrew Rabinovich, Andrea Vedaldi, Carolina Galleg...
ICDE
2006
IEEE
428views Database» more  ICDE 2006»
14 years 10 months ago
Integrating Unstructured Data into Relational Databases
In this paper we present a system for automatically integrating unstructured text into a multi-relational database using state-of-the-art statistical models for structure extracti...
Imran R. Mansuri, Sunita Sarawagi
LREC
2008
130views Education» more  LREC 2008»
13 years 10 months ago
ParsCit: an Open-source CRF Reference String Parsing Package
We describe ParsCit, a freely available, open-source implementation of a reference string parsing package. At the core of ParsCit is a trained conditional random field (CRF) model...
Isaac G. Councill, C. Lee Giles, Min-Yen Kan
IJCV
2008
266views more  IJCV 2008»
13 years 8 months ago
Learning to Recognize Objects with Little Supervision
This paper shows (i) improvements over state-of-the-art local feature recognition systems, (ii) how to formulate principled models for automatic local feature selection in object c...
Peter Carbonetto, Gyuri Dorkó, Cordelia Sch...