Sciweavers

304 search results - page 47 / 61
» Learning Object Categories from Google's Image Search
Sort
View
WSDM
2009
ACM
191views Data Mining» more  WSDM 2009»
14 years 2 months ago
Generating labels from clicks
The ranking function used by search engines to order results is learned from labeled training data. Each training point is a (query, URL) pair that is labeled by a human judge who...
Rakesh Agrawal, Alan Halverson, Krishnaram Kenthap...
APGV
2004
ACM
143views Visualization» more  APGV 2004»
14 years 1 months ago
Perceiving translucent materials
Many common materials, including fruit, wax and human skin, are somewhat translucent. What makes an object look translucent or opaque? Here we use a recently developed computer gr...
Roland W. Fleming, Henrik Wann Jensen, Heinrich H....
ICCV
2011
IEEE
12 years 7 months ago
Discriminative Learning of Relaxed Hierarchy for Large-scale Visual Recognition
In the real visual world, the number of categories a classifier needs to discriminate is on the order of hundreds or thousands. For example, the SUN dataset [24] contains 899 sce...
Tianshi Gao, Daphne Koller
CIKM
2009
Springer
14 years 2 months ago
Helping editors choose better seed sets for entity set expansion
Sets of named entities are used heavily at commercial search engines such as Google, Yahoo and Bing. Acquiring sets of entities typically consists of combining semi-supervised exp...
Vishnu Vyas, Patrick Pantel, Eric Crestan
ECCV
2010
Springer
13 years 9 months ago
Descriptor Learning for Efficient Retrieval
Many visual search and matching systems represent images using sparse sets of "visual words": descriptors that have been quantized by assignment to the best-matching symb...