-
Daniel Huber.
Automatic 3-D Modeling Using Range Images Obtained from Unknown Viewpoints.
In Proceedings of the Third International Conference on 3-D Digital Imaging and Modeling,
pages 153-160,
May 2001.
IEEE Computer Society.
Keywords:
3-D modeling,
registration,
surface matching,
automatic modeling.
@inproceedings{Huber_2001_3746,
author = "Daniel Huber",
title = "Automatic 3-D Modeling Using Range Images Obtained from Unknown Viewpoints",
booktitle = "Proceedings of the Third International Conference on 3-D Digital Imaging and Modeling",
month = "May",
year = "2001",
pages = "153-160",
publisher = "IEEE Computer Society",
keywords="3-D modeling, registration, surface matching, automatic modeling"
}
-
Daniel Huber and
Martial Hebert.
Fully Automatic Registration of Multiple 3-D Data Sets.
In IEEE Computer Society Workshop on Computer Vision Beyond the Visible Spectrum(CVBVS 2001),
December 2001.
(pdf)
Keywords:
3-D perception,
geometric modeling,
3-D modeling,
registration,
surface matching,
automatic modeling.
@inproceedings{Huber_2001_3886,
author = "Daniel Huber and Martial Hebert",
title = "Fully Automatic Registration of Multiple 3-D Data Sets",
booktitle = "IEEE Computer Society Workshop on Computer Vision Beyond the Visible Spectrum(CVBVS 2001)",
month = "December",
year = "2001",
pdf = "http://www.ri.cmu.edu/pub_files/pub3/huber_daniel_f_2001_1/huber_daniel_f_2001_1.pdf",
keywords="3-D perception, geometric modeling, 3-D modeling, registration, surface matching, automatic modeling"
}
-
Shyjan Mahamud,
Martial Hebert, and
Jianbo Shi.
Object Recognition using Boosted Discriminants.
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR '01),
December 2001.
(url)
(pdf)
Abstract: "We approach the task of object discrimination as that of learning efficient "codes" for each object class in terms of responses to a set of chosen discriminants. We formulate this approach in an energy minimization framework. The "code" is built incrementally by successively constructing discriminants that focus on pairs of training images of objects that are currently hard to classify. The particular discriminants that we use partition the set of objects of interest into two well-separated groups. We find the optimal discriminant as well as partition by formulating an objective criteria that measures the well-separateness of the partition. We derive an iterative solution that alternates between the solutions for two generalized eigenproblems, one for the discriminant parameters and the other for the indicator variables denoting the partition. We show how the optimization can easily be biased to focus on hard to classify pairs, which enables us to choose new discriminants one by one in a sequential manner. We validate our approach on a challenging face discrimination task using parts as features and show that it compares favorably with the performance of an eigenspace method."
@inproceedings{Mahamud_2001_4385,
author = "Shyjan Mahamud and Martial Hebert and Jianbo Shi",
title = "Object Recognition using Boosted Discriminants",
booktitle = "Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR '01)",
month = "December",
year = "2001",
url="http://www.ri.cmu.edu/pubs/pub_4385.html",
pdf = "http://www.ri.cmu.edu/pub_files/pub4/mahamud_shyjan_2001_1/mahamud_shyjan_2001_1.pdf",
abstract="We approach the task of object discrimination as that of learning efficient "codes" for each object class in terms of responses to a set of chosen discriminants. We formulate this approach in an energy minimization framework. The "code" is built incrementally by successively constructing discriminants that focus on pairs of training images of objects that are currently hard to classify. The particular discriminants that we use partition the set of objects of interest into two well-separated groups. We find the optimal discriminant as well as partition by formulating an objective criteria that measures the well-separateness of the partition. We derive an iterative solution that alternates between the solutions for two generalized eigenproblems, one for the discriminant parameters and the other for the indicator variables denoting the partition. We show how the optimization can easily be biased to focus on hard to classify pairs, which enables us to choose new discriminants one by one in a sequential manner. We validate our approach on a challenging face discrimination task using parts as features and show that it compares favorably with the performance of an eigenspace method."
}
-
Chuck Rosenberg,
Martial Hebert, and
Sebastian Thrun.
Color constancy using KL-divergence.
In Proceedings of the Eighth IEEE International Conference on Computer Vision (ICCV '01),
volume 1,
pages 239 - 246,
July 2001.
(pdf)
@inproceedings{Rosenberg_2001_3825,
author = "Chuck Rosenberg and Martial Hebert and Sebastian Thrun",
title = "Color constancy using KL-divergence",
booktitle = "Proceedings of the Eighth IEEE International Conference on Computer Vision (ICCV '01)",
month = "July",
year = "2001",
volume = "1",
pages = "239 - 246",
pdf = ""http://www.ri.cmu.edu/pub_files/pub3/rosenberg_chuck_2001_1/rosenberg_chuck_2001_1.pdf"
}
-
Naoya Takao,
Jianbo Shi,
Simon Baker,
Iain Matthews, and
Bart Nabbe.
Tele-Graffiti: A Paper-Based Remote Sketching System.
In Proceedings of the 8th IEEE International Conference on Computer Vision,
Vancouver, British Columbia,
July 2001.
Keywords:
teleconference,
pen and paper human computer interface,
interactive desktop,
camera projector system.
@inproceedings{Takao_2001_3716,
author = "Naoya Takao and Jianbo Shi and Simon Baker and Iain Matthews and Bart Nabbe",
title = "Tele-Graffiti: A Paper-Based Remote Sketching System",
booktitle = "Proceedings of the 8th IEEE International Conference on Computer Vision",
month = "July",
year = "2001",
address = "Vancouver, British Columbia",
keywords="teleconference, pen and paper human computer interface, interactive desktop, camera projector system"
}