146 search results - page 10 / 30 » Learning Metrics Between Tree Structured Data: Application t... |
TNN
2008
14 years 11 months ago
2008
This paper proposes an incremental multiple-object recognition and localization (IMORL) method. The objective of IMORL is to adaptively learn multiple interesting objects in an ima...
161
click to vote
PRIB
2010
Springer
14 years 10 months ago
2010
Springer
Abstract. Supervised classifiers require manually labeled training samples to classify unlabeled objects. Active Learning (AL) can be used to selectively label only “ambiguous...
124
click to vote
CVPR
2012
IEEE
13 years 2 months ago
2012
IEEE
In real-world applications of visual recognition, many factors—such as pose, illumination, or image quality—can cause a significant mismatch between the source domain on whic...
119
click to vote
ICCV
2005
IEEE
2005
IEEE
Mutual Information-Based 3D Surface Matching with Applications to Face Recognition and Brain Mapping
15 years 5 months ago
Face recognition and many medical imaging applications require the computation of dense correspondence vector fields that match one surface with another. In brain imaging, surfac...
104
click to vote
ICMCS
2009
IEEE
14 years 9 months ago
2009
IEEE
Nearest Neighbor (NN) retrieval is a crucial tool of many computer vision tasks. Since the brute-force naive search is too time consuming for most applications, several tailored d...