Abstract. Multiple-instance learning (MIL) allows for training classifiers from ambiguously labeled data. In computer vision, this learning paradigm has been recently used in many ...
We present a new online learning algorithm in the selective sampling framework, where labels must be actively queried before they are revealed. We prove bounds on the regret of ou...
Pedestrian detection in still image should handle the large appearance and pose variations arising from the articulated structure and various clothing of human bodies as well as v...
In this paper, we raise important issues on scalability and the required degree of supervision of existing Mahalanobis metric learning methods. Often rather tedious optimization p...
We present a novel ``dynamic learning'' approach for an intelligent image database system to automatically improve object segmentation and labeling without user interven...