Sciweavers

251 search results - page 45 / 51
» Object Class Recognition by Unsupervised Scale-Invariant Lea...
Sort
View
PRL
2010
158views more  PRL 2010»
13 years 6 months ago
Data clustering: 50 years beyond K-means
: Organizing data into sensible groupings is one of the most fundamental modes of understanding and learning. As an example, a common scheme of scientific classification puts organ...
Anil K. Jain
ICASSP
2010
IEEE
13 years 7 months ago
Weakly supervised learning with decision trees applied to fisheries acoustics
This paper addresses the training of classification trees for weakly labelled data. We call ”weakly labelled data”, a training set such as the prior labelling information pro...
Riwal Lefort, Ronan Fablet, Jean-Marc Boucher
CVPR
2007
IEEE
14 years 9 months ago
Parameter Sensitive Detectors
Object detection can be challenging when the object class exhibits large variations. One commonly-used strategy is to first partition the space of possible object variations and t...
Quan Yuan, Ashwin Thangali, Vitaly Ablavsky, Stan ...
CRV
2011
IEEE
254views Robotics» more  CRV 2011»
12 years 7 months ago
Wavelet Model-based Stereo for Fast, Robust Face Reconstruction
—When reconstructing a specific type or class of object using stereo, we can leverage prior knowledge of the shape of that type of object. A popular class of object to reconstru...
Alan Brunton, Jochen Lang, Eric Dubois, Chang Shu
CVPR
2009
IEEE
15 years 2 months ago
What's It Going to Cost You?: Predicting Effort vs. Informativeness for Multi-Label Image Annotations
Active learning strategies can be useful when manual labeling effort is scarce, as they select the most informative examples to be annotated first. However, for visual category ...
Sudheendra Vijayanarasimhan (University of Texas a...