Sciweavers

399 search results - page 55 / 80
» Robust Boosting for Learning from Few Examples
Sort
View
IJCV
2008
129views more  IJCV 2008»
14 years 11 months ago
Minimal Aspect Distortion (MAD) Mosaicing of Long Scenes
Abstract Long scenes can be imaged by mosaicing multiple images from cameras scanning the scene. We address the case of a video camera scanning a scene while moving in a long path,...
Alex Rav-Acha, Giora Engel, Shmuel Peleg
ICCS
2007
Springer
15 years 5 months ago
Dynamic Tracking of Facial Expressions Using Adaptive, Overlapping Subspaces
We present a Dynamic Data Driven Application System (DDDAS) to track 2D shapes across large pose variations by learning non-linear shape manifold as overlapping, piecewise linear s...
Dimitris N. Metaxas, Atul Kanaujia, Zhiguo Li
NIPS
2003
15 years 1 months ago
One Microphone Blind Dereverberation Based on Quasi-periodicity of Speech Signals
Speech dereverberation is desirable with a view to achieving, for example, robust speech recognition in the real world. However, it is still a challenging problem, especially when...
Tomohiro Nakatani, Masato Miyoshi, Keisuke Kinoshi...
RAS
2007
132views more  RAS 2007»
14 years 11 months ago
Virtual sensors for human concepts - Building detection by an outdoor mobile robot
Abstract— In human-robot communication it is often important to relate robot sensor readings to concepts used by humans. We suggest to use a virtual sensor (one or several physic...
Martin Persson, Tom Duckett, Achim J. Lilienthal
ICRA
2009
IEEE
170views Robotics» more  ICRA 2009»
15 years 6 months ago
Imitation learning with generalized task descriptions
— In this paper, we present an approach that allows a robot to observe, generalize, and reproduce tasks observed from multiple demonstrations. Motion capture data is recorded in ...
Clemens Eppner, Jürgen Sturm, Maren Bennewitz...