Sciweavers

438 search results - page 59 / 88
» The forest hiding problem
Sort
View
ECCV
2010
Springer
15 years 16 hour ago
MIForests: Multiple-Instance Learning with Randomized Trees
Abstract. Multiple-instance learning (MIL) allows for training classifiers from ambiguously labeled data. In computer vision, this learning paradigm has been recently used in many ...
Christian Leistner, Amir Saffari, Horst Bischof
CVPR
2012
IEEE
13 years 2 months ago
Weakly supervised structured output learning for semantic segmentation
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...
Alexander Vezhnevets, Vittorio Ferrari, Joachim M....
ICDE
2009
IEEE
134views Database» more  ICDE 2009»
16 years 1 months ago
Non-Exposure Location Anonymity
Location cloaking has been proposed and well studied to protect user privacy. It blurs the accurate user location (i.e., a point with coordinates) and replaces it with a well-shape...
Haibo Hu, Jianliang Xu
ICIP
2006
IEEE
16 years 1 months ago
Cover Selection for Steganographic Embedding
The primary goal of image steganography techniques has been to maximize embedding rate while minimizing the detectability of the resulting stego images against steganalysis techni...
Mehdi Kharrazi, Taha Taha Sencar, Nasir D. Memon
KDD
2006
ACM
166views Data Mining» more  KDD 2006»
16 years 7 days ago
Anonymizing sequential releases
An organization makes a new release as new information become available, releases a tailored view for each data request, releases sensitive information and identifying information...
Ke Wang, Benjamin C. M. Fung