2295 search results - page 80 / 459 » Learning Overcomplete Representations |
TIP
2008
13 years 8 months ago
2008
Abstract--Sparse representations of signals have drawn considerable interest in recent years. The assumption that natural signals, such as images, admit a sparse decomposition over...
ICIP
2010
IEEE
13 years 6 months ago
2010
IEEE
Representation and measurement are two important issues for saliency models. Different with previous works that learnt sparse features from large scale natural statistics, we prop...
TLT
2008
13 years 8 months ago
2008
While the growing number of learning resources increases the choice for learners on how, what and when to learn, it also makes it more and more difficult to find the learning resou...
AAAI
2012
11 years 11 months ago
2012
Knowledge transfer is computationally challenging, due in part to the curse of dimensionality, compounded by source and target domains expressed using different features (e.g., do...
ICCV
2007
IEEE
14 years 10 months ago
2007
IEEE
Visually extracted 2D and 3D information have their own advantages and disadvantages that complement each other. Therefore, it is important to be able to switch between the differ...