Recognizing human action in non-instrumented video is a challenging task not only because of the variability produced by general scene factors like illumination, background, occlu...
We present an interactive, hybrid human-computer method for object classification. The method applies to classes of objects that are recognizable by people with appropriate expert...
After developing a model free table recognition system we wanted to tune parameters in order to optimize the recognition performance. Therefore we developed a benchmarking environ...
Case-based reasoning (CBR) is a knowledge-based problem-solving technique, which is based on reuse of previous experiences. In this paper we propose a new model for static task as...
We explore an approach to 3D people tracking with learned motion models and deterministic optimization. The tracking problem is formulated as the minimization of a differentiable ...