We study the task of object part extraction and labeling, which seeks to understand objects beyond simply identifiying their bounding boxes. We start from bottom-up segmentation of...
We present a novel multiscale approach that combines segmentation with classification to detect abnormal brain structures in medical imagery, and demonstrate its utility in detect...
The predominant melodic source, frequently the singing voice, is an important component of musical signals. In this paper, we describe a method for extracting the predominant sourc...
Mathieu Lagrange, Luis Gustavo Martins, Jennifer M...
Abstract— We present a general framework for vessel segmentation in retinal images with a particular focus on small vessels. The retinal images are first processed by a nonlinea...
Segmentation and tracking of multiple humans in crowded situations is made difficult by interobject occlusion. We propose a model-based approach to interpret the image observations...