This paper presents a new method of detecting and predicting motion tracking failures with applications in human motion and gait analysis. We define a tracking failure as an event...
Shiloh L. Dockstader, Nikita S. Imennov, A. Murat ...
Predictive state representation (PSR) models for controlled dynamical systems have recently been proposed as an alternative to traditional models such as partially observable Mark...
Michael R. James, Satinder P. Singh, Michael L. Li...
We propose two new data stream models: the reset model and the delta model, motivated by applications to databases, and to tracking the location of spatial points. We present algor...
Michael Hoffmann 0002, S. Muthukrishnan, Rajeev Ra...
Abstract. Building on the current understanding of neural architecture of the visual cortex, we present a graphical model for learning and classification of motion patterns in vid...
Planar motion models can provide gross motion estimation and good segmentation for image pairs with large inter-frame disparity. However, as the disparity becomes larger, the resul...