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...
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...
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...
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...
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...