Sciweavers

ICCV
2009
IEEE
15 years 2 months ago
Bayesian selection of scaling laws for motion modeling in images
Based on scaling laws describing the statistical structure of turbulent motion across scales, we propose a multiscale and non-parametric regularizer for optic-flow estimation. R...
Patrick H´eas, Etienne M´emin, Dominique Heitz, ...
ICCV
2009
IEEE
15 years 2 months ago
3D reconstruction from image collections with a single known focal length
In this paper we aim at reconstructing 3D scenes from images with unknown focal lengths downloaded from photosharing websites such as Flickr. First we provide a minimal solution...
Martin Bujnak, Zuzana Kukelova, Tomas Pajdla
ICCV
2009
IEEE
15 years 2 months ago
A Latent Model of Discriminative Aspect
Recognition using appearance features is confounded by phenomena that cause images of the same object to look different, or images of different objects to look the same. This ma...
Ali Farhadi, Mostafa Kamali Tabrizi, Ian Endres, D...
ICCV
2009
IEEE
3167views Computer Vision» more  ICCV 2009»
15 years 2 months ago
Tracking a Hand Manipulating an Object
We present a method for tracking a hand while it is interacting with an object. This setting is arguably the one where hand-tracking has most practical relevance, but poses signi...
Henning Hamer, Konrad Schindler, Esther Koller-Mei...
ICCV
2009
IEEE
1714views Computer Vision» more  ICCV 2009»
15 years 2 months ago
Power watersheds: a new image segmentation framework extending graph cuts, random walker and optimal spanning forest
In this work, we extend a common framework for seeded image segmentation that includes the graph cuts, ran- dom walker, and shortest path optimization algorithms. Viewing an ima...
Camille Couprie, Leo Grady, Laurent Najman, Hugues...
ICCV
2009
IEEE
15 years 2 months ago
Optimal Correspondences from Pairwise Constraints
Correspondence problems are of great importance in computer vision. They appear as subtasks in many applications such as object recognition, merging partial 3D reconstructions a...
Olof Enqvist, Klas Josephson, Fredrik Kahl
ICCV
2009
IEEE
15 years 2 months ago
Optimizing Parametric Total Variation Models
One of the key factors for the success of recent energy minimization methods is that they seek to compute global solutions. Even for non-convex energy functionals, optimization ...
Petter Strandmark, Fredrik Kahl, Niels Chr. Overga...
ICCV
2009
IEEE
1198views Computer Vision» more  ICCV 2009»
15 years 2 months ago
Implicit Color Segmentation Features for Pedestrian Detection
We investigate the problem of pedestrian detection in still images. Sliding window classifiers, notably using the Histogram-of-Gradient (HOG) features proposed by Dalal and Trig...
Patrick Ott and Mark Everingham
ICCV
2009
IEEE
15 years 2 months ago
Quantifying Contextual Information for Object Detection
Context is critical for minimising ambiguity in object de- tection. In this work, a novel context modelling framework is proposed without the need of any prior scene segmen- tat...
Wei-Shi Zheng, Shaogang Gong and Tao Xiang
ICCV
2009
IEEE
15 years 2 months ago
Feature-Centric Efficient Subwindow Search
embedded in a sliding-window scheme. Such exhaustive search involves massive computation. Efficient Subwindow Search (ESS) [11] avoids this by means of branch and bound. However...
Alain Lehmann, Bastian Leibe, Luc van Gool