Sciweavers

102 search results - page 1 / 21
» A discriminatively trained, multiscale, deformable part mode...
Sort
View
CVPR
2008
IEEE
14 years 6 months ago
A discriminatively trained, multiscale, deformable part model
This paper describes a discriminatively trained, multiscale, deformable part model for object detection. Our system achieves a two-fold improvement in average precision over the b...
Pedro F. Felzenszwalb, David A. McAllester, Deva R...
PAMI
2010
249views more  PAMI 2010»
13 years 3 months ago
Object Detection with Discriminatively Trained Part-Based Models
—We describe an object detection system based on mixtures of multiscale deformable part models. Our system is able to represent highly variable object classes and achieves state-...
Pedro F. Felzenszwalb, Ross B. Girshick, David A. ...
CVPR
2012
IEEE
11 years 7 months ago
Teaching 3D geometry to deformable part models
Current object class recognition systems typically target 2D bounding box localization, encouraged by benchmark data sets, such as Pascal VOC. While this seems suitable for the de...
Bojan Pepik, Michael Stark, Peter V. Gehler, Bernt...
ICCV
2011
IEEE
12 years 4 months ago
Strong Supervision From Weak Annotation: Interactive Training of Deformable Part Models
We propose a framework for large scale learning and annotation of structured models. The system interleaves interactive labeling (where the current model is used to semiautomate t...
Steven Branson, Pietro Perona, Serge Belongie
CVPR
2012
IEEE
11 years 7 months ago
From Pictorial Structures to deformable structures
Pictorial Structures (PS) define a probabilistic model of 2D articulated objects in images. Typical PS models assume an object can be represented by a set of rigid parts connecte...
Silvia Zuffi, Oren Freifeld, Michael J. Black