Sciweavers

150 search results - page 28 / 30
» Shape Discovery from Unlabeled Image Collections
Sort
View
FLAIRS
2004
13 years 11 months ago
A Faster Algorithm for Generalized Multiple-Instance Learning
In our prior work, we introduced a generalization of the multiple-instance learning (MIL) model in which a bag's label is not based on a single instance's proximity to a...
Qingping Tao, Stephen D. Scott
PAMI
2012
12 years 1 days ago
Trainable Convolution Filters and Their Application to Face Recognition
—In this paper, we present a novel image classification system that is built around a core of trainable filter ensembles that we call Volterra kernel classifiers. Our system trea...
Ritwik Kumar, Arunava Banerjee, Baba C. Vemuri, Ha...
CVPR
2010
IEEE
14 years 5 months ago
Efficient Extraction of Human Motion Volumes by Tracking
We present an automatic and efficient method to extract spatio-temporal human volumes from video, which combines top-down model-based and bottom-up appearancebased approaches. Fr...
Juan Carlos Niebles, Bohyung Han, Li Fei-Fei
DAGSTUHL
2006
13 years 11 months ago
Many-to-Many Feature Matching in Object Recognition
One of the bottlenecks of current recognition (and graph matching) systems is their assumption of one-to-one feature (node) correspondence. This assumption breaks down in the gener...
Ali Shokoufandeh, Yakov Keselman, M. Fatih Demirci...
IJDAR
2007
127views more  IJDAR 2007»
13 years 9 months ago
Word matching using single closed contours for indexing handwritten historical documents
Abstract. Effective indexing is crucial for providing convenient access to scanned versions of large collections of handwritten historical manuscripts. Since traditional handwritin...
Tomasz Adamek, Noel E. O'Connor, Alan F. Smeaton