Sciweavers

259 search results - page 45 / 52
» Reinforcement Learning with the Use of Costly Features
Sort
View
JMM2
2006
111views more  JMM2 2006»
13 years 9 months ago
A Microscopic Telepathology System for Multiresolution Computer-Aided Diagnostics
The aim of the presented system is simplification and speedup of the daily pathological examination routine. The system combines telepathology with computer-aided diagnostics algor...
Grigory Begelman, Michael Pechuk, Ehud Rivlin, Edm...
FPL
2009
Springer
85views Hardware» more  FPL 2009»
14 years 1 months ago
Generating high-performance custom floating-point pipelines
Custom operators, working at custom precisions, are a key ingredient to fully exploit the FPGA flexibility advantage for high-performance computing. Unfortunately, such operators...
Florent de Dinechin, Cristian Klein, Bogdan Pasca
TOG
2010
117views more  TOG 2010»
13 years 3 months ago
Multi-feature matching of fresco fragments
We present a multiple-feature approach for determining matches between small fragments of archaeological artifacts such as Bronze-Age and Roman frescoes. In contrast with traditio...
Corey Toler-Franklin, Benedict J. Brown, Tim Weyri...
AAAI
2010
13 years 10 months ago
Efficient Lifting for Online Probabilistic Inference
Lifting can greatly reduce the cost of inference on firstorder probabilistic graphical models, but constructing the lifted network can itself be quite costly. In online applicatio...
Aniruddh Nath, Pedro Domingos
ICCV
2009
IEEE
15 years 2 months ago
Automatic annotation of human actions in video
This paper addresses the problem of automatic temporal annotation of realistic human actions in video using mini- mal manual supervision. To this end we consider two asso- ciate...
Olivier Duchenne, Ivan Laptev, Josef Sivic, Franci...