Sciweavers

10412 search results - page 1350 / 2083
» The efficiency of algorithms - misconceptions
Sort
View
ICCV
2005
IEEE
16 years 9 months ago
Learning Non-Negative Sparse Image Codes by Convex Programming
Example-based learning of codes that statistically encode general image classes is of vital importance for computational vision. Recently, non-negative matrix factorization (NMF) ...
Christoph Schnörr, Matthias Heiler
ICCV
1999
IEEE
16 years 9 months ago
Probabilistic Detection and Tracking of Motion Discontinuities
We propose a Bayesian framework for representing and recognizing local image motion in terms of two primitive models: translation and motion discontinuity. Motion discontinuities ...
Michael J. Black, David J. Fleet
ECCV
2008
Springer
16 years 9 months ago
An Incremental Learning Method for Unconstrained Gaze Estimation
Abstract. This paper presents an online learning algorithm for appearancebased gaze estimation that allows free head movement in a casual desktop environment. Our method avoids the...
Yusuke Sugano, Yasuyuki Matsushita, Yoichi Sato, H...
ECCV
2004
Springer
16 years 9 months ago
Spatially Homogeneous Dynamic Textures
Abstract. We address the problem of modeling the spatial and temporal second-order statistics of video sequences that exhibit both spatial and temporal regularity, intended in a st...
Gianfranco Doretto, Eagle Jones, Stefano Soatto
ECCV
2004
Springer
16 years 9 months ago
Scene and Motion Reconstruction from Defocused and Motion-Blurred Images via Anisotropic Diffusion
We propose a solution to the problem of inferring the depth map, radiance and motion of a scene from a collection of motion-blurred and defocused images. We model motion-blur and d...
Paolo Favaro, Martin Burger, Stefano Soatto
« Prev « First page 1350 / 2083 Last » Next »