Abstract. We describe an efficient approach to construct shape models composed of contour parts with partially-supervised learning. The proposed approach can easily transfer parts ...
We propose a principled framework for recursively segmenting deformable objects across a sequence of frames. We demonstrate the usefulness of this method on left ventricular segmen...
Different from appearance-based methods, clustering feature points only by their motion coherence is an emerging category of approach to detecting and tracking individuals among c...
We present a new active learning approach to incorporate
human feedback for on-line unusual event detection. In contrast to most
existing unsupervised methods that perform passiv...
This paper presents a novel approach of applying both positive selection and negative selection to supervised learning for anomaly detection. It first learns the patterns of the n...