Open Access
2009 IEEE 12th International Conference on Computer Vision (ICCV)
Stephen Gould,Richard Fulton,Daphne Koller,Ido Leichter,Michael Lindenbaum,Thomas Schoenemann,Fredrik Kahl,Daniel Cremers,William Robson Schwartz,David Harwood,Larry S. Davis,Xioayu Wang,Tony X. Han,Subhransu Maji,Alexander C. Berg +14 more
Reads0
Chats0
About:
The article was published on 2009-01-01 and is currently open access. It has received 18 citations till now.read more
Citations
More filters
Proceedings ArticleDOI
Self-weighted Multiple Kernel Learning for Graph-based Clustering and Semi-supervised Classification
TL;DR: In this paper, the authors proposed a novel multiple kernel learning (MKL) framework by following two intuitive assumptions: (i) each kernel is a perturbation of the consensus kernel; and (ii) the kernel that is close to the consensus kernels should be assigned a large weight.
Journal ArticleDOI
Metric Learning for Multi-atlas based Segmentation of Hippocampus.
TL;DR: A novel metric learning method to fuse segmentation labels in multi-atlas based image segmentation by learning a distance metric model from the atlases to keep image patches of the same structure close to each other while those of different structures are separated.
Journal ArticleDOI
Recovering Relative Depth from Low-Level Features Without Explicit T-junction Detection and Interpretation
Felipe Calderero,Vicent Caselles +1 more
TL;DR: This work presents a novel computational model for relative depth order estimation from a single image based on low-level local features that encode perceptual depth cues such as convexity/concavity, inclusion, and T-junctions in a quantitative manner, considering information at different scales.
Dissertation
Understanding and predicting where people look in images
TL;DR: A new way to model where people look from ground truth eye tracking data is described using techniques of machine learning that outperforms all existing models, and a benchmark data set is provided to quantitatively compare existing and future models.
Discontinuous Galerkin FEM in computer graphics
TL;DR: DG FEM is applied in the context of physically-based simulation of deformable solids and shells, as well as image warping, where it enables applications such as the efficient simulation of progressive cutting, dynamic mesh refinement, and a novel mesh generation approach.
References
More filters
Proceedings ArticleDOI
An algebraic approach to affine registration of point sets
TL;DR: This paper formulates a least-squares problem for matching moments of the two distributions up to degree three, and the resulting cost function is a polynomial that can be efficiently optimized using techniques originated from algebraic geometry.