Abstract | ||
---|---|---|
Current models of object recognition generally assume a bottom-up process within a hierarchy of stages. As an alternative, we present a top-down modulation of the processed stimulus information to allow a goal-directed detection of objects within natural scenes. Our procedure has its origin in current findings of research in attention which suggest that feedback enhances cells in a feature-specific manner. We show that feedback allows discrimination of a target object by allocation of attentional resources. |
Year | DOI | Venue |
---|---|---|
2002 | 10.1007/3-540-36181-2_40 | Biologically Motivated Computer Vision |
Keywords | Field | DocType |
object recognition,object detection,natural scene,attentional resource,natural scenes,target object,current model,goal-directed detection,feature-specific manner,current finding,processed stimulus information,bottom-up process,bottom up,top down | Deep-sky object,Object detection,Computer vision,Object-class detection,Computer science,Artificial intelligence,Stimulus (physiology),Hierarchy,Form perception,Cognitive neuroscience of visual object recognition | Conference |
Volume | ISSN | ISBN |
2525 | 0302-9743 | 3-540-00174-3 |
Citations | PageRank | References |
4 | 0.71 | 3 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Fred Henrik Hamker | 1 | 34 | 8.13 |
James Worcester | 2 | 9 | 1.87 |