Recognizing 3D objects from arbitrary view points is one of the most fundamental problems in computer vision. A major challenge lies in the transition between the 3D geometry of o...
This paper presents a new approach for multi-view object class detection. Appearance and geometry are treated as separate learning tasks with different training data. Our approach...
This paper describes a machine learning approach for visual
object detection which is capable of processing images
extremely rapidly and achieving high detection rates. This
wor...
The bounding box representation employed by many popular object detection models [3, 6] implicitly assumes all pixels inside the box belong to the object. This assumption makes th...
We present an object class detection approach which fully integrates the complementary strengths offered by shape matchers. Like an object detector, it can learn class models dire...