Sciweavers

180 search results - page 31 / 36
» Learning to segment from a few well-selected training images
Sort
View
WWW
2004
ACM
14 years 9 months ago
Learning block importance models for web pages
Some previous works show that a web page can be partitioned to multiple segments or blocks, and usually the importance of those blocks in a page is not equivalent. Also, it is pro...
Ruihua Song, Haifeng Liu, Ji-Rong Wen, Wei-Ying Ma
ICTAI
2008
IEEE
14 years 3 months ago
Veritas: Combining Expert Opinions without Labeled Data
We consider a variation of the problem of combining expert opinions for the situation in which there is no ground truth to use for training. Even though we don’t have labeled da...
Sharath R. Cholleti, Sally A. Goldman, Avrim Blum,...
IJRR
2008
109views more  IJRR 2008»
13 years 8 months ago
Robotic Grasping of Novel Objects using Vision
We consider the problem of grasping novel objects, specifically ones that are being seen for the first time through vision. Grasping a previously unknown object, one for which a 3...
Ashutosh Saxena, Justin Driemeyer, Andrew Y. Ng
ICML
2010
IEEE
13 years 9 months ago
Submodular Dictionary Selection for Sparse Representation
We develop an efficient learning framework to construct signal dictionaries for sparse representation by selecting the dictionary columns from multiple candidate bases. By sparse,...
Andreas Krause, Volkan Cevher
ENGL
2007
164views more  ENGL 2007»
13 years 8 months ago
Vision Based Target-Tracking Realized with Mobile Robots using Extended Kalman Filter
— The paper presents a novel scheme for target-tracking realized with two mobile robots, where one robot is configured as tracker and the other as moving target. Fuzzy C-means cl...
Sheli Sinha Chaudhuri, Amit Konar