The Community for Technology Leaders
RSS Icon
Providence, RI
June 16, 2012 to June 21, 2012
ISBN: 978-1-4673-1226-4
pp: 3130-3137
I. Endres , Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
We cast the problem of recognizing related categories as a unified learning and structured prediction problem with shared body plans. When provided with detailed annotations of objects and their parts, these body plans model objects in terms of shared parts and layouts, simultaneously capturing a variety of categories in varied poses. We can use these body plans to jointly train many detectors in a shared framework with structured learning, leading to significant gains for each supervised task. Using our model, we can provide detailed predictions of objects and their parts for both familiar and unfamiliar categories.
object recognition, learning (artificial intelligence), unfamiliar category, shared body plans, related categor recognition, unified learning, structured prediction problem, detailed object annotations, shared parts, shared layouts, shared framework, structured learning, supervised task, detailed object prediction, Detectors, Layout, Deformable models, Animals, Legged locomotion, Joints, Training
I. Endres, "Learning shared body plans", CVPR, 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2012, pp. 3130-3137, doi:10.1109/CVPR.2012.6248046
469 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool