While low-dimensional image representations have been very popular in computer vision, they suffer from two limitations: (i) they require collecting a large and varied training se...
People detection is an important task for a wide range of applications in computer vision. State-of-the-art methods learn appearance based models requiring tedious collection and ...
Leonid Pishchulin, Christian Wojek, Arjun Jain, Th...
This paper presents a technique to learn dynamic appearance models from a small number of training frames. Under this framework, dynamic appearance is modelled as an unknown opera...
We derive a probabilistic framework for robust, real-time, visual tracking of previously unseen objects from a moving camera. The tracking problem is handled using a bag-of-pixels ...
Tracking people or objects across multiple cameras is a challenging research area in visual computing especially when these cameras have non-overlapping field-of-views. The import...