Sciweavers

267 search results - page 27 / 54
» Unsupervised Learning of Event Classes from Video
Sort
View
ICMCS
2000
IEEE
138views Multimedia» more  ICMCS 2000»
15 years 2 months ago
Event-Coupled Hidden Markov Models
Inferences from time-series data can be greatly enhanced by taking into account multiple modalities. In some cases, such as audio of speech and the corresponding video of lip gest...
Trausti T. Kristjansson, Brendan J. Frey, Thomas S...
CVPR
2011
IEEE
14 years 7 months ago
Learning Better Image Representations Using 'Flobject Analysis'
Unsupervised learning can be used to extract image representations that are useful for various and diverse vision tasks. After noticing that most biological vision systems for int...
Inmar Givoni, Patrick Li, Brendan Frey
ICDM
2009
IEEE
117views Data Mining» more  ICDM 2009»
15 years 4 months ago
Discriminative Mixed-Membership Models
Although mixed-membership models have achieved great success in unsupervised learning, they have not been widely applied to classification problems. In this paper, we propose a f...
Hanhuai Shan, Arindam Banerjee, Nikunj C. Oza
CVPR
2009
IEEE
16 years 4 months ago
Actions in context
This paper exploits the context of natural dynamic scenes for human action recognition in video. Human actions are frequently constrained by the purpose and the physical propert...
Marcin Marszalek (INRIA), Ivan Laptev (INRIA), Cor...
NIPS
1997
14 years 11 months ago
Learning Human-like Knowledge by Singular Value Decomposition: A Progress Report
Singular value decomposition (SVD) can be viewed as a method for unsupervised training of a network that associates two classes of events reciprocally by linear connections throug...
Thomas K. Landauer, Darrell Laham, Peter W. Foltz