We propose an approach for detecting objects in large-scale range datasets that combines bottom-up and top-down processes. In the bottom-up stage, fast-to-compute local descriptors are used to detect potential target objects. The object hypotheses are verified after alignment in a top-down stage using global descriptors that capture larger scale structure information. We have found that the com...

The MMI-007 project uses both bottom-up and top-down strategies to deal with the difficult problem of object recognition in outdoor scenes. Within this scheme, bottom-up methods fulfil the requirements of providing a concise image description suitable for symbolic reasoning and of providing an initial set of hypotheses to 'bootstrap' the top-down processes. The nature of the imagery does not le...

in Proc. IEEE Int’l Conf. on Image Processing 2001, Thessaloniki, Greece To track multiple objects, top-down (model-based methods) and bottom-up (multi-layer analysis) methods have been proposed separately. In this paper, a hierarchical MRF model is proposed to integrate these two trends into a MAP framework for tracking non-rigid objects such as human hands or faces. Parametric models of color...

The present study investigated the relative contribution of bottom-up and top-down control to task selection in the voluntary task-switching (VTS) procedure. In order to manipulate the efficiency of top-down control, a concurrent working memory load was imposed during VTS. In three experiments, bottom-up factors, such as stimulus repetitions, repetition of irrelevant information, and stimulus-t...