Sciweavers

568 search results - page 28 / 114
» Saccadic Object Recognition with an Active Vision System
Sort
View
ICVS
2001
Springer
14 years 25 days ago
Adapting Object Recognition across Domains: A Demonstration
High-level vision systems use object, scene or domain specific knowledge to interpret images. Unfortunately, this knowledge has to be acquired for every domain. This makes it diffi...
Bruce A. Draper, Ulrike Ahlrichs, Dietrich Paulus
EUROGP
2009
Springer
143views Optimization» more  EUROGP 2009»
13 years 6 months ago
A Real-Time Evolutionary Object Recognition System
We have created a real-time evolutionary object recognition system. Genetic Programming is used to automatically search the space of possible computer vision programs guided throug...
Marc Ebner
CVPR
2006
IEEE
14 years 2 months ago
Recognition of Composite Human Activities through Context-Free Grammar Based Representation
This paper describes a general methodology for automated recognition of complex human activities. The methodology uses a context-free grammar (CFG) based representation scheme to ...
Michael S. Ryoo, J. K. Aggarwal
CVPR
2009
IEEE
15 years 3 months ago
What's It Going to Cost You?: Predicting Effort vs. Informativeness for Multi-Label Image Annotations
Active learning strategies can be useful when manual labeling effort is scarce, as they select the most informative examples to be annotated first. However, for visual category ...
Sudheendra Vijayanarasimhan (University of Texas a...
ROBOCUP
2004
Springer
103views Robotics» more  ROBOCUP 2004»
14 years 1 months ago
A Constructive Feature Detection Approach for Robotic Vision
We describe a new method for detecting features on a marked RoboCup field. We implemented the framework for robots with omnidirectional vision, but the method can be easily adapte...
Felix von Hundelshausen, Michael Schreiber, Ra&uac...