TY - GEN
T1 - Motion fused frames
T2 - 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
AU - Kopuklu, Okan
AU - Kose, Neslihan
AU - Rigoll, Gerhard
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/12/13
Y1 - 2018/12/13
N2 - Acquiring spatio-temporal states of an action is the most crucial step for action classification. In this paper, we propose a data level fusion strategy, Motion Fused Frames (MFFs), designed to fuse motion information into static images as better representatives of spatio-temporal states of an action. MFFs can be used as input to any deep learning architecture with very little modification on the network. We evaluate MFFs on hand gesture recognition tasks using three video datasets-Jester, ChaLearn LAP IsoGD and NVIDIA Dynamic Hand Gesture Datasets-which require capturing long-term temporal relations of hand movements. Our approach obtains very competitive performance on Jester and ChaLearn benchmarks with the classification accuracies of 96.28% and 57.4%, respectively, while achieving state-of-the-art performance with 84.7% accuracy on NVIDIA benchmark.
AB - Acquiring spatio-temporal states of an action is the most crucial step for action classification. In this paper, we propose a data level fusion strategy, Motion Fused Frames (MFFs), designed to fuse motion information into static images as better representatives of spatio-temporal states of an action. MFFs can be used as input to any deep learning architecture with very little modification on the network. We evaluate MFFs on hand gesture recognition tasks using three video datasets-Jester, ChaLearn LAP IsoGD and NVIDIA Dynamic Hand Gesture Datasets-which require capturing long-term temporal relations of hand movements. Our approach obtains very competitive performance on Jester and ChaLearn benchmarks with the classification accuracies of 96.28% and 57.4%, respectively, while achieving state-of-the-art performance with 84.7% accuracy on NVIDIA benchmark.
UR - http://www.scopus.com/inward/record.url?scp=85060881573&partnerID=8YFLogxK
U2 - 10.1109/CVPRW.2018.00284
DO - 10.1109/CVPRW.2018.00284
M3 - Conference contribution
AN - SCOPUS:85060881573
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 2184
EP - 2192
BT - Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
PB - IEEE Computer Society
Y2 - 18 June 2018 through 22 June 2018
ER -