Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Onur C. Hamsici"'
Autor:
Onur C. Hamsici, Aleix M. Martinez
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 31:1985-1999
Shape analysis requires invariance under translation, scale, and rotation. Translation and scale invariance can be realized by normalizing shape vectors with respect to their mean and norm. This maps the shape feature vectors onto the surface of a hy
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::62d9a81119a7a65357c1d62d2e8ad720
https://doi.org/10.1109/tpami.2008.234
https://doi.org/10.1109/tpami.2008.234
Autor:
Onur C. Hamsici, Aleix M. Martinez
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 30:647-657
We present an algorithm which provides the one-dimensional subspace where the Bayes error is minimized for the C class problem with homoscedastic Gaussian distributions. Our main result shows that the set of possible one-dimensional spaces v, for whi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8e4564a333553ab8e8bacc7c55fbaa6b
https://doi.org/10.1109/tpami.2007.70717
https://doi.org/10.1109/tpami.2007.70717
Autor:
Aleix M. Martinez, Onur C. Hamsici
Human preferences are usually measured using ordinal variables. A system whose goal is to estimate the preferences of humans and their underlying decision mechanisms requires to learn the ordering of any given sample set. We consider the solution of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9d0f4735b5adf1781b6e25a876b90890
https://europepmc.org/articles/PMC4848170/
https://europepmc.org/articles/PMC4848170/
Publikováno v:
CVPR
Learning models for object detection is a challenging problem due to the large intra-class variability of objects in appearance, viewpoints, and rigidity. We address this variability by a novel feature pooling method that is adaptive to segmented reg
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::871ae7ac7d806dde0b36dde2fd12f496
https://doi.org/10.1109/cvpr.2015.7298673
https://doi.org/10.1109/cvpr.2015.7298673
Publikováno v:
Computer Vision – ECCV 2012 ISBN: 9783642337642
ECCV (4)
ECCV (4)
Non-rigid structure from motion (NRSFM) is a classical underconstrained problem in computer vision. A common approach to make NRSFM more tractable is to constrain 3D shape deformation to be smooth over time. This constraint has been used to compress
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::983f26b2a2442bf417173d470d600c43
https://europepmc.org/articles/PMC3740973/
https://europepmc.org/articles/PMC3740973/
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 33(3)
Kernel mapping is one of the most used approaches to intrinsically derive nonlinear classifiers. The idea is to use a kernel function which maps the original nonlinearly separable problem to a space of intrinsically larger dimensionality where the cl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7caf909018281442e9d258c27e89676b
https://pubmed.ncbi.nlm.nih.gov/20820072
https://pubmed.ncbi.nlm.nih.gov/20820072
Publikováno v:
SPIE Proceedings.
A number of popular image matching algorithms such as Scale Invariant Feature Transform (SIFT)1 are based on local image features. They first detect interest points (or keypoints) across an image and then compute descriptors based on patches around t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fc90ec6ae9b2444b5825953a06113766
https://doi.org/10.1117/12.862359
https://doi.org/10.1117/12.862359
Autor:
Aleix M. Martinez, Onur C. Hamsici
Publikováno v:
Pattern recognition. 41(11)
Many problems in paleontology reduce to finding those features that best discriminate among a set of classes. A clear example is the classification of new specimens. However, these classifications are generally challenging because the number of discr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6899e356c7e40acaad0f605e6f42278f
https://pubmed.ncbi.nlm.nih.gov/19884951
https://pubmed.ncbi.nlm.nih.gov/19884951
Autor:
Onur C. Hamsici, Aleix M. Martinez
Publikováno v:
ICCV
2D Active Appearance Models (AAM) and 3D Morphable Models (3DMM) are widely used techniques. AAM provide a fast fitting process, but may represent unwanted 3D transformations unless strictly constrained not to do so. The reverse is true for 3DMM. The
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f1bfe11b14f2445cd54c19c6dbdc1b39
https://doi.org/10.1109/iccv.2009.5459365
https://doi.org/10.1109/iccv.2009.5459365