Sparse representations using overcomplete dictionaries are used in a variety of field such as pattern recognition and compression. However, the size of dictionary is usually a tra...
The supremacy of n-gram models in statistical language modelling has recently been challenged by parametric models that use distributed representations to counteract the difficult...
Many difficult visual perception problems, like 3D human motion estimation, can be formulated in terms of inference using complex generative models, defined over high-dimensional ...
We propose a novel boosting algorithm which improves on current algorithms for weighted voting classification by striking a better balance between classification accuracy and the ...
Automatic image tagging is important yet challenging due to the semantic gap and the lack of learning examples to model a tag’s visual diversity. Meanwhile, social user tagging ...