Sciweavers

4277 search results - page 423 / 856
» On Multiple Linear Approximations
Sort
View
CVPR
2012
IEEE
13 years 2 months ago
Multi-class cosegmentation
Bottom-up, fully unsupervised segmentation remains a daunting challenge for computer vision. In the cosegmentation context, on the other hand, the availability of multiple images ...
Armand Joulin, Francis Bach, Jean Ponce
ICML
2008
IEEE
16 years 20 days ago
On the quantitative analysis of deep belief networks
Deep Belief Networks (DBN's) are generative models that contain many layers of hidden variables. Efficient greedy algorithms for learning and approximate inference have allow...
Ruslan Salakhutdinov, Iain Murray
ALGOSENSORS
2007
Springer
15 years 6 months ago
Assigning Sensors to Missions with Demands
We introduce Semi-Matching with Demands (SMD), which models a certain problem in sensor networks of assigning individual sensors to sensing tasks. If there are multiple sensing tas...
Amotz Bar-Noy, Theodore Brown, Matthew P. Johnson,...
CSCLP
2007
Springer
15 years 6 months ago
Combining Two Structured Domains for Modeling Various Graph Matching Problems
Abstract. Graph pattern matching is a central application in many fields. In various areas, the structure of the pattern can only be approximated and exact matching is then too ac...
Yves Deville, Grégoire Dooms, Stépha...
WINE
2007
Springer
151views Economy» more  WINE 2007»
15 years 6 months ago
Computing Optimal Bundles for Sponsored Search
A context in sponsored search is additional information about a query, such as the user’s age, gender or location, that can change an advertisement’s relevance or an advertise...
Arpita Ghosh, Hamid Nazerzadeh, Mukund Sundararaja...