We develop a multi-class object detection framework whose core component is a nearest neighbor search over object part classes. The performance of the overall system is critically...
This paper presents an online learning algorithm to construct from video sequences an image-based representation that is useful for recognition and tracking. For a class of object...
Abstract. This paper presents a method for tracking multiple skincolored objects in images acquired by a possibly moving camera. The proposed method encompasses a collection of tec...
In recent years, anonymization methods have emerged as an important tool to preserve individual privacy when releasing privacy sensitive data sets. This interest in anonymization t...
In digital fingerprinting and multimedia forensic systems, it is possible that multiple adversaries mount attacks collectively and effectively to undermine the forensic system...