![]() |
| |||||||||||||
DIFF-CVML 2017 : 3rd International Workshop on DIFFerential Geometry in Computer Vision and Machine Learning (in conjunction with CVPR 2017) | |||||||||||||
Link: http://www-rech.telecom-lille.fr/diffcvml2017/index.html | |||||||||||||
| |||||||||||||
Call For Papers | |||||||||||||
Riemannian geometric computing has received a lot of recent interest in the computer vision community. In particular, Riemannian geometric principles can be applied to a variety of difficult computer vision problems including face recognition, activity recognition, object detection, biomedical image analysis, and structure-from-motion to name a few. Besides their nice mathematical formulation, Riemannian computations based on the geometry of underlying manifolds are often faster and more stable than their classical counterparts. Over the past few years, the popularity of Riemannian algorithms has increased several-fold. Some of the mathematical entities that benefit from a geometric analysis include rotation matrices, medial representations, subspace comparisons, symmetric positive-definite matrices, function spaces, and many more. The topics of interest for this workshop include, but are not limited to:
• Shape Representations: Silhouettes, Surfaces, Skeletons, Humans, etc.. • Information Geometry: Fisher-Rao and elastic metrics, Gromov-Wasserstein family, Earth- Mover’s distance, etc. • Dynamical Systems: Trajectories on manifolds, Rate-invariance, Identification and classification of systems. • Domain Transfer: Ideas and applications. • Image/Volume/Trajectory: Spatial and temporal registration & segmentation. • Manifold-Valued Features: Histograms, Covariances, Symmetric positive-definite matrices, Mixture models. • Big Data: Dimension-reduction using geometric tools. • Bayesian Inferences: Nonlinear domains, Computationalsolutions using differential geometry, Variational approaches. • Machine Learning Approaches on Nonlinear Feature Spaces: Kernel methods, Boosting, SVM-type classification, Detection and tracking algorithms. • Functional Data Analysis: Hilbert manifolds, Visualization. • Applications: Medical analysis, Biometrics, Biology, Environmetrics, Graphics, Activity recognition, Bioinformatics, Pattern recognition, etc. • Geometry of Articulated Bodies: Applications to robotics, biomechanics, and motor control. • Computational Topology and Applications. Original papers related to the topics of interest listed above can be submitted through the workshop webpage. Papers covering theory and/or application areas of computer vision are invited for submission. All papers will be reviewed under the double blind review process. Submitted papers should follow the same formatting style as a CVPR conference paper. |
|