Sciweavers

2512 search results - page 93 / 503
» Learning from Highly Structured Data by Decomposition
Sort
View
ICCV
2009
IEEE
16 years 2 months ago
Decomposing a Scene into Geometric and Semantically Consistent Regions
High-level, or holistic, scene understanding involves reasoning about objects, regions, and the 3D relationships between them. This requires a representation above the level of ...
Stephen Gould, Richard Fulton, Daphne Koller
SLSFS
2005
Springer
15 years 3 months ago
Incorporating Constraints and Prior Knowledge into Factorization Algorithms - An Application to 3D Recovery
Abstract. Matrix factorization is a fundamental building block in many computer vision and machine learning algorithms. In this work we focus on the problem of ”structure from mo...
Amit Gruber, Yair Weiss
CIDR
2009
148views Algorithms» more  CIDR 2009»
14 years 11 months ago
The Case for a Structured Approach to Managing Unstructured Data
The challenge of managing unstructured data represents perhaps the largest data management opportunity for our community since managing relational data. And yet we are risking let...
AnHai Doan, Jeffrey F. Naughton, Akanksha Baid, Xi...
CORR
2004
Springer
125views Education» more  CORR 2004»
14 years 9 months ago
High-Level Networking With Mobile Code And First Order AND-Continuations
We describe a scheme for moving living code between a set of distributed processes coordinated with unification based Linda operations, and its application to building a comprehen...
Paul Tarau, Verónica Dahl
ACL
2007
14 years 11 months ago
A fully Bayesian approach to unsupervised part-of-speech tagging
Unsupervised learning of linguistic structure is a difficult problem. A common approach is to define a generative model and maximize the probability of the hidden structure give...
Sharon Goldwater, Tom Griffiths