We introduce a framework for defining a distance on the (non-Euclidean) space of Linear Dynamical Systems (LDSs). The proposed distance is induced by the action of the group of o...
For scene classification, patch-level linear features do not always work as well as handcrafted features. In this paper, we present a new model to greatly improve the usefulness ...
Liwei Wang, Yin Li, Jiaya Jia, Jian Sun, David Wip...
In this paper, we propose an approach to accurately localize detected objects. The goal is to predict which features pertain to the object and define the object extent with segme...
In this paper, we address the task of tracking groups of people in surveillance scenarios. This is a major challenge in computer vision, since groups are structured entities, subj...
We present a hierarchical model for human activity recognition in entire multi-person scenes. Our model describes human behaviour at multiple levels of detail, ranging from low-le...