Sciweavers

211 search results - page 2 / 43
» Adapting Object Recognition across Domains: A Demonstration
Sort
View
CVPR
2011
IEEE
12 years 11 months ago
What You Saw is Not What You Get: Domain Adaptation Using Asymmetric Kernel Transforms
In real-world applications, “what you saw” during training is often not “what you get” during deployment: the distribution and even the type and dimensionality of features...
Brian Kulis, Kate Saenko, Trevor Darrell
MM
2009
ACM
178views Multimedia» more  MM 2009»
13 years 10 months ago
Semantic context transfer across heterogeneous sources for domain adaptive video search
Automatic video search based on semantic concept detectors has recently received significant attention. Since the number of available detectors is much smaller than the size of h...
Yu-Gang Jiang, Chong-Wah Ngo, Shih-Fu Chang
PRL
2007
125views more  PRL 2007»
13 years 3 months ago
Combining color and spatial information for object recognition across illumination changes
One of the most widely used approaches in the context of object recognition across illumination changes consists in comparing the images by means of the intersection between invar...
Damien Muselet, Ludovic Macaire
ECCV
2008
Springer
14 years 5 months ago
Training Hierarchical Feed-Forward Visual Recognition Models Using Transfer Learning from Pseudo-Tasks
Abstract. Building visual recognition models that adapt across different domains is a challenging task for computer vision. While feature-learning machines in the form of hierarchi...
Amr Ahmed, Kai Yu, Wei Xu, Yihong Gong, Eric P. Xi...
AAAI
2006
13 years 5 months ago
LOCATE Intelligent Systems Demonstration: Adapting Help to the Cognitive Styles of Users
LOCATE is workspace layout design software that also serves as a testbed for developing and refining principles of adaptive aiding. This demonstration illustrates LOCATE's ab...
Jack L. Edwards, Greg Scott