Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/424210
Full metadata record
DC FieldValueLanguage
dc.contributorHewitt, Robinen_US
dc.contributorBelongie, Sergeen_US
dc.date2006en_US
dc.date.accessioned2020-05-18T12:18:29Z-
dc.date.available2020-05-18T12:18:29Z-
dc.date.issued2008en_US
dc.identifier.other10.1109/CVPRW.2006.23en_US
dc.identifier.urihttp://localhost/handle/Hannan/373579en_US
dc.identifier.urihttp://localhost/handle/Hannan/424210-
dc.descriptionen_US
dc.descriptionen_US
dc.descriptionen_US
dc.description.abstractThis paper describes a method by which a computer can autonomously acquire training data for learning to recognize a user's face. The computer, in this method, actively seeks out opportunities to acquire informative face examples. Using the principles of co-training, it combines a face detector trained on a single input image with tracking to extract face examples for learning. Our results show that this method extracts well-localized, diverse face examples from video after being introduced to the user through only one input image. In addition to requiring very little human intervention, a second significant benefit to this method is that it doesn't rely on a statistical classifier trained on a pre-existing face database for face detection. Because it doesn't require pre-training, this method has built-in robustness for situations where the application conditions differ from the conditions under which training data were acquired. © 2006 IEEE.en_US
dc.relation.haspartAL501435.pdfen_US
dc.subjectActive Learning in Face Recognition: Using Tracking to Build a Face Modelen_US
dc.titleActive learning in face recognition: Using tracking to build a face modelen_US
dc.typeArticleen_US
dc.journal.titleProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognitionen_US
Appears in Collections:2002-2008

Files in This Item:
File SizeFormat 
AL501435.pdf906.89 kBAdobe PDF
Full metadata record
DC FieldValueLanguage
dc.contributorHewitt, Robinen_US
dc.contributorBelongie, Sergeen_US
dc.date2006en_US
dc.date.accessioned2020-05-18T12:18:29Z-
dc.date.available2020-05-18T12:18:29Z-
dc.date.issued2008en_US
dc.identifier.other10.1109/CVPRW.2006.23en_US
dc.identifier.urihttp://localhost/handle/Hannan/373579en_US
dc.identifier.urihttp://localhost/handle/Hannan/424210-
dc.descriptionen_US
dc.descriptionen_US
dc.descriptionen_US
dc.description.abstractThis paper describes a method by which a computer can autonomously acquire training data for learning to recognize a user's face. The computer, in this method, actively seeks out opportunities to acquire informative face examples. Using the principles of co-training, it combines a face detector trained on a single input image with tracking to extract face examples for learning. Our results show that this method extracts well-localized, diverse face examples from video after being introduced to the user through only one input image. In addition to requiring very little human intervention, a second significant benefit to this method is that it doesn't rely on a statistical classifier trained on a pre-existing face database for face detection. Because it doesn't require pre-training, this method has built-in robustness for situations where the application conditions differ from the conditions under which training data were acquired. © 2006 IEEE.en_US
dc.relation.haspartAL501435.pdfen_US
dc.subjectActive Learning in Face Recognition: Using Tracking to Build a Face Modelen_US
dc.titleActive learning in face recognition: Using tracking to build a face modelen_US
dc.typeArticleen_US
dc.journal.titleProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognitionen_US
Appears in Collections:2002-2008

Files in This Item:
File SizeFormat 
AL501435.pdf906.89 kBAdobe PDF
Full metadata record
DC FieldValueLanguage
dc.contributorHewitt, Robinen_US
dc.contributorBelongie, Sergeen_US
dc.date2006en_US
dc.date.accessioned2020-05-18T12:18:29Z-
dc.date.available2020-05-18T12:18:29Z-
dc.date.issued2008en_US
dc.identifier.other10.1109/CVPRW.2006.23en_US
dc.identifier.urihttp://localhost/handle/Hannan/373579en_US
dc.identifier.urihttp://localhost/handle/Hannan/424210-
dc.descriptionen_US
dc.descriptionen_US
dc.descriptionen_US
dc.description.abstractThis paper describes a method by which a computer can autonomously acquire training data for learning to recognize a user's face. The computer, in this method, actively seeks out opportunities to acquire informative face examples. Using the principles of co-training, it combines a face detector trained on a single input image with tracking to extract face examples for learning. Our results show that this method extracts well-localized, diverse face examples from video after being introduced to the user through only one input image. In addition to requiring very little human intervention, a second significant benefit to this method is that it doesn't rely on a statistical classifier trained on a pre-existing face database for face detection. Because it doesn't require pre-training, this method has built-in robustness for situations where the application conditions differ from the conditions under which training data were acquired. © 2006 IEEE.en_US
dc.relation.haspartAL501435.pdfen_US
dc.subjectActive Learning in Face Recognition: Using Tracking to Build a Face Modelen_US
dc.titleActive learning in face recognition: Using tracking to build a face modelen_US
dc.typeArticleen_US
dc.journal.titleProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognitionen_US
Appears in Collections:2002-2008

Files in This Item:
File SizeFormat 
AL501435.pdf906.89 kBAdobe PDF