The problem of multibody motion segmentation is an important and challenging issue in computer vision. In this paper, a novel segmentation technique based on simulated annealing (...
Standard pattern recognition provides effective and noise-tolerant tools for machine learning tasks; however, most approaches only deal with real vectors of a finite and fixed dime...
This paper introduces a new approach to actionvalue function approximation by learning basis functions from a spectral decomposition of the state-action manifold. This paper exten...
This paper presents a method for automatic recognition of human gestures. The method works with 3D image data from a range camera to achieve invariance to viewpoint. The recogniti...
We introduce an online learning approach for multitarget tracking. Detection responses are gradually associated into tracklets in multiple levels to produce final tracks. Unlike ...