Multiple instance (MI) learning is a recent learning paradigm that is more flexible than standard supervised learning algorithms in the handling of label ambiguity. It has been u...
This paper presents an approach to multi-sensory and multi-modal fusion in which computer vision information obtained from calibrated cameras is integrated with a large-scale sent...
Boosting has been widely applied in computer vision, especially after Viola and Jones's seminal work [23]. The marriage of rectangular features and integral-imageenabled fast...
Abstract. With the rapid development of fast data acquisition techniques, 3D scans that record the geometric and photometric information of deformable objects are routinely acquire...
Detecting shadows from images can significantly improve the performance of several vision tasks such as object detection and tracking. Recent approaches have mainly used illuminat...