Sciweavers

1112 search results - page 57 / 223
» Novel image feature alphabets for object recognition
Sort
View
CVPR
2011
IEEE
14 years 5 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
CVPR
2010
IEEE
1248views Computer Vision» more  CVPR 2010»
15 years 6 months ago
Food Recognition Using Statistics of Pairwise Local Features
Food recognition is difficult because food items are deformable objects that exhibit significant variations in appearance. We believe the key to recognizing food is to exploit the...
Shulin Yang, Mei Chen, Dean Pomerleau, Rahul Sukth...
CVPR
2005
IEEE
15 years 11 months ago
Automatic Face Recognition for Film Character Retrieval in Feature-Length Films
The objective of this work is to recognize all the frontal faces of a character in the closed world of a movie or situation comedy, given a small number of query faces. This is ch...
Ognjen Arandjelovic, Andrew Zisserman
AAAI
1996
14 years 11 months ago
A Hybrid Learning Approach for Better Recognition of Visual Objects
Real world images often contain similar objects but with different rotations, noise, or other visual alterations. Vision systems should be able to recognize objects regardless of ...
Ibrahim F. Imam, Srinivas Gutta
KDD
2012
ACM
183views Data Mining» more  KDD 2012»
13 years 7 days ago
Mining discriminative components with low-rank and sparsity constraints for face recognition
This paper introduces a novel image decomposition approach for an ensemble of correlated images, using low-rank and sparsity constraints. Each image is decomposed as a combination...
Qiang Zhang, Baoxin Li