Accurate, well-calibrated estimates of class membership probabilities are needed in many supervised learning applications, in particular when a cost-sensitive decision must be mad...
We address an unsupervised object detection and segmentation problem that goes beyond the conventional assumptions of one-to-one object correspondences or model-test settings betwe...
Minsu Cho (Seoul National University), Young Min S...
Probabilistic branching node inference is an important step for analyzing branching patterns involved in many anatomic structures. We propose combining machine learning techniques...
Haibin Ling, Michael Barnathan, Vasileios Megalooi...
Speaker diarization is originally defined as the task of determining “who spoke when” given an audio track and no other prior knowledge of any kind. The following article sho...
The Fisher kernel is a generic framework which combines the benefits of generative and discriminative approaches to pattern classification. In this contribution, we propose to a...