We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (Learning Object Classes with Unsupervised Segmentation...
We are interested in modeling the variability of different images of the same scene, or class of objects, obtained by changing the imaging conditions, for instance the viewpoint o...
Jeremy D. Jackson, Anthony J. Yezzi, Stefano Soatt...
Probabilistic relational models are an efficient way to learn and represent the dynamics in realistic environments consisting of many objects. Autonomous intelligent agents that gr...
Tracking multiple objects is important in many application domains. We propose a novel algorithm for multi-object tracking that is capable of working under very challenging conditi...
This paper describes methods for recovering time-varying shape and motion of nonrigid 3D objects from uncalibrated 2D point tracks. For example, given a video recording of a talkin...
Lorenzo Torresani, Aaron Hertzmann, Christoph Breg...