Sciweavers

ACL
2012
12 years 1 months ago
Collective Generation of Natural Image Descriptions
We present a holistic data-driven approach to image description generation, exploiting the vast amount of (noisy) parallel image data and associated natural language descriptions ...
Polina Kuznetsova, Vicente Ordonez, Alexander C. B...
IAT
2010
IEEE
13 years 9 months ago
Getting What You Pay For: Is Exploration in Distributed Hill Climbing Really Worth it?
Abstract--The Distributed Stochastic Algorithm (DSA), Distributed Breakout Algorithm (DBA), and variations such as Distributed Simulated Annealing (DSAN), MGM-1, and DisPeL, are di...
Melanie Smith, Roger Mailler
IJCAI
2007
14 years 26 days ago
Symmetric Component Caching
Caching, symmetries, and search with decomposition are powerful techniques for pruning the search space of constraint problems. In this paper we present an innovative way of effi...
Matthew Kitching, Fahiem Bacchus
CSCLP
2008
Springer
14 years 1 months ago
Robust Solutions in Unstable Optimization Problems
We consider constraint optimization problems where costs (or preferences) are all given, but some are tagged as possibly unstable, and provided with a range of alternative values. ...
Maria Silvia Pini, Francesca Rossi, Kristen Brent ...
CP
2008
Springer
14 years 1 months ago
Exploiting Decomposition in Constraint Optimization Problems
Decomposition is a powerful technique for reducing the size of a backtracking search tree. However, when solving constraint optimization problems (COP's) the standard techniqu...
Matthew Kitching, Fahiem Bacchus
AAAI
2008
14 years 1 months ago
H-DPOP: Using Hard Constraints for Search Space Pruning in DCOP
In distributed constraint optimization problems, dynamic programming methods have been recently proposed (e.g. DPOP). In dynamic programming many valuations are grouped together i...
Akshat Kumar, Adrian Petcu, Boi Faltings
ATAL
2005
Springer
14 years 5 months ago
Preprocessing techniques for accelerating the DCOP algorithm ADOPT
Methods for solving Distributed Constraint Optimization Problems (DCOP) have emerged as key techniques for distributed reasoning. Yet, their application faces significant hurdles...
Syed Muhammad Ali, Sven Koenig, Milind Tambe