This paper proposes a new randomized strategy for adaptive MCMC using Bayesian optimization. This approach applies to nondifferentiable objective functions and trades off explor...
Human visual capability has remained largely beyond the reach of engineered systems despite intensive study and considerable progress in problem understanding, algorithms and comp...
We introduce a framework for syntactic parsing with latent variables based on a form of dynamic Sigmoid Belief Networks called Incremental Sigmoid Belief Networks. We demonstrate ...
Illuminant estimation from shadows typically relies on accurate segmentation of the shadows and knowledge of exact 3D geometry, while shadow estimation is difficult in the presen...
Cloth modeling and recognition is an important and challenging problem in both vision and graphics tasks, such as dressed human recognition and tracking, human sketch and portrait...