TY - GEN
T1 - Learning from summaries of videos
T2 - 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops, CVPRW 2010
AU - Chakraborty, Shayok
AU - Balasubramanian, Vineeth
AU - Panchanathan, Sethuraman
PY - 2010
Y1 - 2010
N2 - Against the backdrop of growing concerns about security and privacy, biometrics has emerged as a methodology to reliably infer the identity of an individual. In biometric applications like face recognition, real world data is usually generated in batches such as frames of video in a capture session. The captured data has high redundancy and it is a significant challenge to select the most promising instances from this superfluous set for training a classifier. Active learning methods select only the salient instances for annotation and have gained popularity to reduce the number of examples required to learn a classification model. Typical active learning techniques select one example from an unlabeled set at a time and the classifier is retrained after every selected example. However, there have been very limited efforts in this field to select a batch of salient instances at one shot to update the classification model. In this work, a novel batch mode active learning scheme, specifically tailored to handle the high redundancy of biometric data, has been formulated and validated on the person recognition problem. The instance selection is ased on numerical optimization of an objective function, which can be adapted to suit the requirements of a particular application and to integrate additional available information. The results obtained on the widely used VidTIMIT and the NIST MBGC datasets certify the potential of this method in being used for real world biometric recognition problems.
AB - Against the backdrop of growing concerns about security and privacy, biometrics has emerged as a methodology to reliably infer the identity of an individual. In biometric applications like face recognition, real world data is usually generated in batches such as frames of video in a capture session. The captured data has high redundancy and it is a significant challenge to select the most promising instances from this superfluous set for training a classifier. Active learning methods select only the salient instances for annotation and have gained popularity to reduce the number of examples required to learn a classification model. Typical active learning techniques select one example from an unlabeled set at a time and the classifier is retrained after every selected example. However, there have been very limited efforts in this field to select a batch of salient instances at one shot to update the classification model. In this work, a novel batch mode active learning scheme, specifically tailored to handle the high redundancy of biometric data, has been formulated and validated on the person recognition problem. The instance selection is ased on numerical optimization of an objective function, which can be adapted to suit the requirements of a particular application and to integrate additional available information. The results obtained on the widely used VidTIMIT and the NIST MBGC datasets certify the potential of this method in being used for real world biometric recognition problems.
UR - http://www.scopus.com/inward/record.url?scp=77956496674&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77956496674&partnerID=8YFLogxK
U2 - 10.1109/CVPRW.2010.5544617
DO - 10.1109/CVPRW.2010.5544617
M3 - Conference contribution
AN - SCOPUS:77956496674
SN - 9781424470297
T3 - 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops, CVPRW 2010
SP - 130
EP - 137
BT - 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops, CVPRW 2010
Y2 - 13 June 2010 through 18 June 2010
ER -