Sciweavers

2527 search results - page 340 / 506
» Discrete optimization in computer vision
Sort
View
CVPR
2008
IEEE
16 years 6 months ago
Viewpoint-independent object class detection using 3D Feature Maps
This paper presents a 3D approach to multi-view object class detection. Most existing approaches recognize object classes for a particular viewpoint or combine classifiers for a f...
Joerg Liebelt, Cordelia Schmid, Klaus Schertler
ECCV
2008
Springer
16 years 6 months ago
Using Multiple Hypotheses to Improve Depth-Maps for Multi-View Stereo
We propose an algorithm to improve the quality of depth-maps used for Multi-View Stereo (MVS). Many existing MVS techniques make use of a two stage approach which estimates depth-m...
Carlos Hernández, George Vogiatzis, Neill D...
ECCV
2010
Springer
15 years 2 months ago
Coupled Gaussian Process Regression for Pose-Invariant Facial Expression Recognition
We present a novel framework for the recognition of facial expressions at arbitrary poses that is based on 2D geometric features. We address the problem by first mapping the 2D loc...
Ognjen Rudovic, Ioannis Patras, Maja Pantic
CVPR
2012
IEEE
13 years 7 months ago
Video segmentation by tracing discontinuities in a trajectory embedding
Our goal is to segment a video sequence into moving objects and the world scene. In recent work, spectral embedding of point trajectories based on 2D motion cues accumulated from ...
Katerina Fragkiadaki, Geng Zhang, Jianbo Shi
GECCO
2008
Springer
239views Optimization» more  GECCO 2008»
15 years 5 months ago
Multiobjective design of operators that detect points of interest in images
In this paper, a multiobjective (MO) learning approach to image feature extraction is described, where Pareto-optimal interest point (IP) detectors are synthesized using genetic p...
Leonardo Trujillo, Gustavo Olague, Evelyne Lutton,...