Sciweavers

64 search results - page 6 / 13
» Context-dependent kernel design for object matching and reco...
Sort
View
ICCV
2007
IEEE
14 years 9 months ago
Active Learning with Gaussian Processes for Object Categorization
Discriminative methods for visual object category recognition are typically non-probabilistic, predicting class labels but not directly providing an estimate of uncertainty. Gauss...
Ashish Kapoor, Kristen Grauman, Raquel Urtasun, Tr...
ICMCS
2008
IEEE
131views Multimedia» more  ICMCS 2008»
14 years 1 months ago
A novel contextual descriptors for category recognition
In this paper, we propose a novel contextual descriptor which combines the contextual information and local appearance. Based on Gibbs distribution, a local descriptor is designed...
Yi Ouyang, Ming Tang, Jian Cheng, Jinqiao Wang, Ha...
CVPR
2003
IEEE
14 years 9 months ago
Recognizing Objects in Adversarial Clutter: Breaking a Visual CAPTCHA
In this paper we explore object recognition in clutter. We test our object recognition techniques on Gimpy and EZGimpy, examples of visual CAPTCHAs. A CAPTCHA ("Completely Au...
Greg Mori, Jitendra Malik
MM
2010
ACM
462views Multimedia» more  MM 2010»
13 years 7 months ago
KPB-SIFT: a compact local feature descriptor
Invariant feature descriptors such as SIFT and GLOH have been demonstrated to be very robust for image matching and object recognition. However, such descriptors are typically of ...
Gangqiang Zhao, Ling Chen, Gencai Chen, Junsong Yu...
GECCO
2009
Springer
258views Optimization» more  GECCO 2009»
14 years 2 days ago
Evolutionary learning of local descriptor operators for object recognition
Nowadays, object recognition is widely studied under the paradigm of matching local features. This work describes a genetic programming methodology that synthesizes mathematical e...
Cynthia B. Pérez, Gustavo Olague