Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

10

ICML
2005
IEEE

favoriteEmaildiscussreport

99views Machine Learning» more ICML 2005»

Object correspondence as a machine learning problem

14 years 5 months ago

Object correspondence as a machine learning problem

Download www.machinelearning.org

We propose machine learning methods for the estimation of deformation fields that transform two given objects into each other, thereby establishing a dense point to point correspondence. The fields are computed using a modified support vector machine containing a penalty enforcing that points of one object will be mapped to "similar" points on the other one. Our system, which contains little engineering or domain knowledge, delivers state of the art performance. We present application results including close to photorealistic morphs of 3D head models.

Bernhard Schölkopf, Florian Steinke, Volker B

Real-time Traffic

Deformation Fields | ICML 2005 | Machine Learning | Machine Learning Methods | Support Vector Machine |

claim paper

Related Content

» Label Ranking under Ambiguous Supervision for Learning Semantic Correspondences

» Learning Object Correspondences with the Observed Transport Shape Measure

» Ranking on graph data

» Robust 3D object registration without explicit correspondence using geometric integration

» Learned color constancy from local correspondences

» MultiModal Hierarchical Dirichlet Process Model for Predicting Image Annotation and ImageO...

» Learning the Kernel Combination for Object Categorization

» Local Ensemble Kernel Learning for Object Category Recognition

» Combining Generative Models and Fisher Kernels for Object Recognition

Post Info
More Details (n/a)

Added	17 Nov 2009
Updated	17 Nov 2009
Type	Conference
Year	2005
Where	ICML
Authors	Bernhard Schölkopf, Florian Steinke, Volker Blanz

Comments (0)