Motion Key-Frame Extraction by Using Optimized t-Stochastic Neighbor Embedding

Key-frame extracting technology has been widely used in the field of human motion synthesis. Efficient and accurate key frames extraction methods can improve the accuracy of motion synthesis. In this paper, we use an optimized t-Stochastic Neighbor Embedding (t-SNE for short) algorithm to reduce the data and on this basis extract the key frames. The experimental results show that the validity of this method is better than the existing methods under the same experimental data.

[1]  Eric O. Postma,et al.  Dimensionality Reduction: A Comparative Review , 2008 .

[2]  Ahmed M. Elgammal,et al.  Human Motion Synthesis by Motion Manifold Learning and Motion Primitive Segmentation , 2006, AMDO.

[3]  Yasuhiko Sakamoto,et al.  Motion map: image-based retrieval and segmentation of motion data , 2004, SCA '04.

[4]  Laurens van der Maaten,et al.  Learning a Parametric Embedding by Preserving Local Structure , 2009, AISTATS.

[5]  Meinard Müller,et al.  Motion templates for automatic classification and retrieval of motion capture data , 2006, SCA '06.

[6]  Kilian Q. Weinberger,et al.  Stochastic triplet embedding , 2012, 2012 IEEE International Workshop on Machine Learning for Signal Processing.

[7]  Christoph Bregler,et al.  Motion capture assisted animation: texturing and synthesis , 2002, ACM Trans. Graph..

[8]  Abdullah Bade,et al.  Motion Graph for Character Animation: Design Considerations , 2009, 2009 International Conference on Computer Technology and Development.

[9]  Jessica K. Hodgins,et al.  Hierarchical Aligned Cluster Analysis for Temporal Clustering of Human Motion , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Max Welling,et al.  Hidden-Unit Conditional Random Fields , 2011, AISTATS.

[11]  Bobby Bodenheimer,et al.  Using nonlinear dimensionality reduction in 3D figure animation , 2005, ACM Southeast Regional Conference.

[12]  Michael Gleicher,et al.  Automated extraction and parameterization of motions in large data sets , 2004, SIGGRAPH 2004.

[13]  Jessica K. Hodgins,et al.  Interactive control of avatars animated with human motion data , 2002, SIGGRAPH.

[14]  Lucas Kovar,et al.  Motion graphs , 2002, SIGGRAPH Classes.

[15]  Geoffrey E. Hinton,et al.  Stochastic Neighbor Embedding , 2002, NIPS.

[16]  Laurens van der Maaten,et al.  Fast Optimization for t-SNE , 2010 .

[17]  Arno Zinke,et al.  Fast local and global similarity searches in large motion capture databases , 2010, SCA '10.

[18]  Jernej Barbic,et al.  Segmenting Motion Capture Data into Distinct Behaviors , 2004, Graphics Interface.

[19]  Qiang Zhang,et al.  Key Frames Extraction of Human Motion Capture Data Based on Cosine Similarity , 2017 .

[20]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[21]  Hans-Peter Seidel,et al.  Efficient and Robust Annotation of Motion Capture Data , 2009 .

[22]  Sung Yong Shin,et al.  On-line locomotion generation based on motion blending , 2002, SCA '02.

[23]  Lucas Kovar,et al.  Motion Graphs , 2002, ACM Trans. Graph..

[24]  Geoffrey E. Hinton,et al.  Visualizing non-metric similarities in multiple maps , 2011, Machine Learning.

[25]  Tido Röder,et al.  Efficient content-based retrieval of motion capture data , 2005, SIGGRAPH 2005.

[26]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[27]  Reinhard Klein,et al.  Efficient unsupervised temporal segmentation of human motion , 2014, SCA '14.

[28]  Alla Safonova,et al.  Achieving good connectivity in motion graphs , 2008, SCA '08.