571 search results - page 14 / 115 » One person labels one million images |
CVPR
2012
IEEE
11 years 11 months ago
2012
IEEE
In machine learning and computer vision, input signals are often filtered to increase data discriminability. For example, preprocessing face images with Gabor band-pass filters ...
KDD
2012
ACM
11 years 11 months ago
2012
ACM
Multi-label learning arises in many real-world tasks where an object is naturally associated with multiple concepts. It is well-accepted that, in order to achieve a good performan...
KDD
2009
ACM
14 years 9 months ago
2009
ACM
Many scalable data mining tasks rely on active learning to provide the most useful accurately labeled instances. However, what if there are multiple labeling sources (`oracles...
AAAI
2007
13 years 10 months ago
2007
In semi-supervised learning, a number of labeled examples are usually required for training an initial weakly useful predictor which is in turn used for exploiting the unlabeled e...
ICCV
2009
IEEE
15 years 1 months ago
2009
IEEE
One of the main limitations of image search based on
bag-of-features is the memory usage per image. Only a few
million images can be handled on a single machine in rea-
sonable ...