Contextual Modulation of Target Saliency
Antonio B. Torralba · 2001
The most popular algorithms for object detection require the use of exhaustive spatial and scale search procedures. In such approaches, an object is defined by means of local features. In this paper we show that including contextual information in object detection procedures provides an efficient way of cutting down the need for exhaustive search. We present results with real images showing that the proposed scheme is able to accurately predict likely object classes, locations and sizes.