Kernel methods provide an efficient mechanism to derive nonlinear algorithms. In classification problems as well as in feature extraction, kernel-based approaches map the original...
This paper overviews a new gesture recognition framework
based on learning local motion signatures (LMSs) introduced
by [1]. After the generation of these LMSs computed
on one i...
We present a method to segment a collection of unlabeled images while exploiting automatically discovered appearance patterns shared between them. Given an unlabeled pool of multi...
Recent advances in scene understanding and related tasks
have highlighted the importance of using regions to reason
about high-level scene structure. Typically, the regions are
...
There are many computer vision algorithms developed for visual (scene and object) recognition. Some systems focus on involved learning algorithms, some leverage millions of trainin...