Sign In

Communications of the ACM

Research highlights

Using the Forest to See the Trees: Exploiting Context for Visual Object Detection and Localization


tree in forest

Recognizing objects in images is an active area of research in computer vision. However, most of the algorithms for detecting objects perform an exhaustive search across all locations and scales in the image comparing local image regions with an object model. That approach ignores the semantic structure of scenes and tries to solve the recognition problem by brute force.