Sciweavers

422 search results - page 48 / 85
» Online Selection of Tracking Features using AdaBoost
Sort
View
ICCV
2007
IEEE
16 years 6 months ago
Scene Summarization for Online Image Collections
We formulate the problem of scene summarization as selecting a set of images that efficiently represents the visual content of a given scene. The ideal summary presents the most i...
Ian Simon, Noah Snavely, Steven M. Seitz
ICFHR
2010
151views Biometrics» more  ICFHR 2010»
14 years 11 months ago
Error Reduction by Confusing Characters Discrimination for Online Handwritten Japanese Character Recognition
To reduce the classification errors of online handwritten Japanese character recognition, we propose a method for confusing characters discrimination with little additional costs....
Xiang-Dong Zhou, Da-Han Wang, Masaki Nakagawa, Che...
CVPR
2009
IEEE
15 years 8 months ago
Learning to associate: HybridBoosted multi-target tracker for crowded scene
We propose a learning-based hierarchical approach of multi-target tracking from a single camera by progressively associating detection responses into longer and longer track fragm...
Yuan Li, Chang Huang, Ram Nevatia
ECIR
2010
Springer
15 years 5 months ago
Learning to Select a Ranking Function
Abstract. Learning To Rank (LTR) techniques aim to learn an effective document ranking function by combining several document features. While the function learned may be uniformly ...
Jie Peng, Craig Macdonald, Iadh Ounis
ICARCV
2002
IEEE
153views Robotics» more  ICARCV 2002»
15 years 9 months ago
Fast, unconstrained camera motion estimation from stereo without tracking and robust statistics
Camera motion estimation is useful for a range of applications. Usually, feature tracking is performed through the sequence of images to determine correspondences. Furthermore, ro...
Heiko Hirschmüller, Peter R. Innocent, Jonath...