89 search results - page 11 / 18 » Selecting What Is Important: Training Visual Attention |
ICCV
2011
IEEE
12 years 7 months ago
2011
IEEE
Traditional supervised visual learning simply asks annotators “what” label an image should have. We propose an approach for image classification problems requiring subjective...
NAACL
2003
13 years 8 months ago
2003
e by placing terms in an abstract ‘information space’ based on their occurrences in text corpora, and then allowing a user to visualize local regions of this information space....
CVPR
2012
IEEE
11 years 10 months ago
2012
IEEE
We address the problem of weakly supervised semantic segmentation. The training images are labeled only by the classes they contain, not by their location in the image. On test im...
WWW
2010
ACM
14 years 2 months ago
2010
ACM
We introduce a new dissimilarity function for ranked lists, the expected weighted Hoeffding distance, that has several advantages over current dissimilarity measures for ranked s...
COLING
2008
13 years 9 months ago
2008
Most studies in statistical or machine learning based authorship attribution focus on two or a few authors. This leads to an overestimation of the importance of the features extra...