Sciweavers

1997 search results - page 39 / 400
» The importance of being biased
Sort
View
MM
1997
ACM
117views Multimedia» more  MM 1997»
14 years 25 days ago
What Should a Wildebeest Say? Interactive Nature Films for High School Classrooms
Nature documentaries play an important role in high school biology classrooms, yet they deliver a passive and biased account of the behavior of organisms. To engage students in mo...
Brian K. Smith, Brian J. Reiser
ACCV
2007
Springer
14 years 20 days ago
Unsupervised Identification of Multiple Objects of Interest from Multiple Images: dISCOVER
Given a collection of images of offices, what would we say we see in the images? The objects of interest are likely to be monitors, keyboards, phones, etc. Such identification of t...
Devi Parikh, Tsuhan Chen
HAIS
2009
Springer
14 years 15 days ago
Beyond Homemade Artificial Data Sets
One of the most important challenges in supervised learning is how to evaluate the quality of the models evolved by different machine learning techniques. Up to now, we have relied...
Núria Macià, Albert Orriols-Puig, Es...
DAGM
2008
Springer
13 years 10 months ago
An Unbiased Second-Order Prior for High-Accuracy Motion Estimation
Abstract. Virtually all variational methods for motion estimation regularize the gradient of the flow field, which introduces a bias towards piecewise constant motions in weakly te...
Werner Trobin, Thomas Pock, Daniel Cremers, Horst ...
UAI
2008
13 years 10 months ago
Hybrid Variational/Gibbs Collapsed Inference in Topic Models
Variational Bayesian inference and (collapsed) Gibbs sampling are the two important classes of inference algorithms for Bayesian networks. Both have their advantages and disadvant...
Max Welling, Yee Whye Teh, Bert Kappen