Sciweavers

5692 search results - page 152 / 1139
» Challenges and Unsolved Problems
Sort
View
122
Voted
JMLR
2012
13 years 3 months ago
Structured Output Learning with High Order Loss Functions
Often when modeling structured domains, it is desirable to leverage information that is not naturally expressed as simply a label. Examples include knowledge about the evaluation ...
Daniel Tarlow, Richard S. Zemel
FOCS
2005
IEEE
15 years 6 months ago
Mechanism Design via Machine Learning
We use techniques from sample-complexity in machine learning to reduce problems of incentive-compatible mechanism design to standard algorithmic questions, for a wide variety of r...
Maria-Florina Balcan, Avrim Blum, Jason D. Hartlin...
95
Voted
MM
2005
ACM
145views Multimedia» more  MM 2005»
15 years 6 months ago
Multiple instance learning for labeling faces in broadcasting news video
Labeling faces in news video with their names is an interesting research problem which was previously solved using supervised methods that demand significant user efforts on lab...
Jun Yang 0003, Rong Yan, Alexander G. Hauptmann
121
Voted
GEOINFO
2003
15 years 2 months ago
Planning Brazilian Urban Traffic with a Geographic Application Software
Planning and optimizing urban traffic is a difficult problem, with considerable economic and social impacts. The development of suitable software tools to aid municipal governments...
Juliano Lopes de Oliveira, André Constantin...
CTW
2006
112views more  CTW 2006»
15 years 27 days ago
Cross border railway operations: improving safety at cultural interfaces
Organizations with different cultures will be increasingly required to interface with each other as legislation is introduced to ensure the interoperability of railway systems acr...
S. O. Johnsen, J. Vatn, R. Rosness, I. A. Herrera