Sciweavers

488 search results - page 82 / 98
» Point labeling with sliding labels
Sort
View
ICMCS
1999
IEEE
202views Multimedia» more  ICMCS 1999»
13 years 12 months ago
A Human-Assisted System to Build 3-D Models from a Single Image
We present a system at the junction between Computer Vision and Computer Graphics, to produce a 3-D model of an object as observed in a single image, with a minimum of high-level ...
Alexandre R. J. François, Gérard G. ...
CIDM
2007
IEEE
13 years 11 months ago
Efficient Kernel-based Learning for Trees
Kernel methods are effective approaches to the modeling of structured objects in learning algorithms. Their major drawback is the typically high computational complexity of kernel ...
Fabio Aiolli, Giovanni Da San Martino, Alessandro ...
DIS
2007
Springer
13 years 11 months ago
Time and Space Efficient Discovery of Maximal Geometric Graphs
A geometric graph is a labeled graph whose vertices are points in the 2D plane with an isomorphism invariant under geometric transformations such as translation, rotation, and scal...
Hiroki Arimura, Takeaki Uno, Shinichi Shimozono
CLEAR
2006
Springer
109views Biometrics» more  CLEAR 2006»
13 years 11 months ago
Evaluation of Head Pose Estimation for Studio Data
This paper introduces our head pose estimation system that localizes nose-tip of the faces and estimates head poses in studio quality pictures. After the nose-tip in the training d...
Jilin Tu, Yun Fu, Yuxiao Hu, Thomas S. Huang
ECML
2006
Springer
13 years 11 months ago
Active Learning with Irrelevant Examples
Abstract. Active learning algorithms attempt to accelerate the learning process by requesting labels for the most informative items first. In real-world problems, however, there ma...
Dominic Mazzoni, Kiri Wagstaff, Michael C. Burl