TY - GEN
T1 - Multiresolution match kernels for gesture video classification
AU - Demakethepalli Venkateswara, Hemanth
AU - Balasubramanian, Vineeth N.
AU - Lade, Prasanth
AU - Panchanathan, Sethuraman
PY - 2013
Y1 - 2013
N2 - The emergence of depth imaging technologies like the Microsoft Kinect has renewed interest in computational methods for gesture classification based on videos. For several years now, researchers have used the Bag-of-Features (BoF) as a primary method for generation of feature vectors from video data for recognition of gestures. However, the BoF method is a coarse representation of the information in a video, which often leads to poor similarity measures between videos. Besides, when features extracted from different spatio-temporal locations in the video are pooled to create histogram vectors in the BoF method, there is an intrinsic loss of their original locations in space and time. In this paper, we propose a new Multiresolution Match Kernel (MMK) for video classification, which can be considered as a generalization of the BoF method. We apply this procedure to hand gesture classification based on RGB-D videos of the American Sign Language(ASL) hand gestures and our results show promise and usefulness of this new method.
AB - The emergence of depth imaging technologies like the Microsoft Kinect has renewed interest in computational methods for gesture classification based on videos. For several years now, researchers have used the Bag-of-Features (BoF) as a primary method for generation of feature vectors from video data for recognition of gestures. However, the BoF method is a coarse representation of the information in a video, which often leads to poor similarity measures between videos. Besides, when features extracted from different spatio-temporal locations in the video are pooled to create histogram vectors in the BoF method, there is an intrinsic loss of their original locations in space and time. In this paper, we propose a new Multiresolution Match Kernel (MMK) for video classification, which can be considered as a generalization of the BoF method. We apply this procedure to hand gesture classification based on RGB-D videos of the American Sign Language(ASL) hand gestures and our results show promise and usefulness of this new method.
KW - Bag of Features
KW - Gesture Recognition
KW - Multiple Kernels
KW - Spatio-temporal Pyramid
UR - http://www.scopus.com/inward/record.url?scp=84888218485&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84888218485&partnerID=8YFLogxK
U2 - 10.1109/ICMEW.2013.6618279
DO - 10.1109/ICMEW.2013.6618279
M3 - Conference contribution
AN - SCOPUS:84888218485
SN - 9781479916047
T3 - Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013
BT - Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013
T2 - 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013
Y2 - 15 July 2013 through 19 July 2013
ER -