Sciweavers

1601 search results - page 199 / 321
» Learning Gaussian processes from multiple tasks
Sort
View
VISAPP
2008
15 years 4 months ago
Towards the Estimation of Conspicuity with Visual Priors
Traffic signs are designed to be clearly seen by drivers. However a little is known about the visual influence of the traffic sign environment on how it will be perceived. Computer...
Ludovic Simon, Jean-Philippe Tarel, Roland Bremond
IJCNN
2007
IEEE
15 years 9 months ago
Two-stage Multi-class AdaBoost for Facial Expression Recognition
— Although AdaBoost has achieved great success, it still suffers from following problems: (1) the training process could be unmanageable when the number of features is extremely ...
Hongbo Deng, Jianke Zhu, Michael R. Lyu, Irwin Kin...
CORR
2010
Springer
121views Education» more  CORR 2010»
14 years 10 months ago
Deep Self-Taught Learning for Handwritten Character Recognition
Recent theoretical and empirical work in statistical machine learning has demonstrated the importance of learning algorithms for deep architectures, i.e., function classes obtaine...
Frédéric Bastien, Yoshua Bengio, Arn...
IJON
2008
116views more  IJON 2008»
15 years 3 months ago
Discovering speech phones using convolutive non-negative matrix factorisation with a sparseness constraint
Discovering a representation that allows auditory data to be parsimoniously represented is useful for many machine learning and signal processing tasks. Such a representation can ...
Paul D. O'Grady, Barak A. Pearlmutter
108
Voted
TKDE
2008
116views more  TKDE 2008»
15 years 3 months ago
Long-Term Cross-Session Relevance Feedback Using Virtual Features
Relevance feedback (RF) is an iterative process, which refines the retrievals by utilizing the user's feedback on previously retrieved results. Traditional RF techniques solel...
Peng-Yeng Yin, Bir Bhanu, Kuang-Cheng Chang, Anlei...