Many vision problems can be cast as optimizing the conditional probability density function p(C|I) where I is an image and C is a vector of model parameters describing the image. ...
Jingdan Zhang, Shaohua Kevin Zhou, Dorin Comaniciu...
We present two novel methods to automatically learn spatio-temporal dependencies of moving agents in complex dynamic scenes. They allow to discover temporal rules, such as the rig...
Daniel Kuettel, Michael Breitenstein, Luc Van Gool...
Spatial priors play crucial roles in many high-level vision tasks, e.g. scene understanding. Usually, learning spatial priors relies on training a structured output model. In this...
End-to-end distortion estimation plays an important role in error-resilient video coding. The intuitive method is to simulate the decoding process many times at the encoder, as use...
Model-based testing as a black-box testing technique has grown in importance. The models used represent the relevant features of the system under consideration (SUC), and can also...