Abstract. An object recognition process in general is designed as a domain specific, highly specialized task. As the complexity of such a process tends to be rather inestimable, m...
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...
We present an active learning approach to choose image annotation requests among both object category labels and the objects’ attribute labels. The goal is to solicit those labe...
This paper presents a semi-supervised learning (SSL) approach to find similarities of images using statistics of local matches. SSL algorithms are well known for leveraging a larg...
Suppose a set of images contains frequent occurrences of objects from an unknown category. This paper is aimed at simultaneously solving the following related problems: (1) unsupe...