Article

Multifactor Gaussian process models for style-content separation

Authors:

David J. Fleet,

Aaron HertzmannAuthors Info & Claims

ICML '07: Proceedings of the 24th international conference on Machine learning

Pages 975 - 982

https://doi.org/10.1145/1273496.1273619

Published: 20 June 2007 Publication History

Abstract

We introduce models for density estimation with multiple, hidden, continuous factors. In particular, we propose a generalization of multilinear models using nonlinear basis functions. By marginalizing over the weights, we obtain a multifactor form of the Gaussian process latent variable model. In this model, each factor is kernelized independently, allowing nonlinear mappings from any particular factor to the data. We learn models for human locomotion data, in which each pose is generated by factors representing the person's identity, gait, and the current state of motion. We demonstrate our approach using time-series prediction, and by synthesizing novel animation from the model.

References

[1]

Brand, M., & Hertzmann, A. (2000). Style machines. ACM SIGGRAPH (pp. 183--192).

Digital Library

[2]

De Lathauwer, L., De Moor, B., & Vandewalle, J. (2000). A multilinear singular value decomposition. SIAM Journal on Matrix Analysis and Applications, 21, 1253--1278.

Digital Library

[3]

Elgammal, A., & Lee, C.-S. (2004). Separating style and content on a nonlinear manifold. IEEE Conf. Comp. Vis. and Pattern Recognition (pp. 478--485). Vol. 1.

[4]

Grassia, F. S. (1998). Practical parameterization of rotations using the exponential map. JGT, 3, 29--48.

Digital Library

[5]

Grochow, K., Martin, S. L., Hertzmann, A., & Popovi&cacute;ć, Z. (2004). Style-based inverse kinematics. ACM Transactions on Graphics, 23, 522--531. Proc. SIGGRAPH.

Digital Library

[6]

Lawrence, N. D. (2005). Probabilistic non-linear principal component analysis with Gaussian process latent variable models. J. Machine Learning Res., 6, 1783--1816.

Digital Library

[7]

Li, Y., Du, Y., & Lin, X. (2005). Kernel-based multifactor analysis for image synthesis and recognition. IEEE Inter. Conf. Comp. Vis. (ICCV) (pp. 114--119). Vol. 1.

Digital Library

[8]

Rasmussen, C. E., & Williams, C. K. I. (2006). Gaussian Processes for Machine Learning. The MIT Press.

Digital Library

[9]

Rose, C., Cohen, M. F., & Bodenheimer, B. (1998). Verbs and adverbs: Multidimensional motion interpolation. IEEE Computer Graphics and Applications, 18, 32--40.

Digital Library

[10]

Rose, C., Sloan, P.-P. J., & Cohen, M. F. (2001). Artist-directed inverse-kinematics using radial basis function interpolation. Computer Graphics Forum, 20. Proc. EG.

[11]

Shapiro, A., Cao, Y., & Faloutsos, P. (2006). Style components. Graphics Interface (pp. 33--40).

Digital Library

[12]

Sidenbladh, H., Black, M. J., & Fleet, D. J. (2000). Stochastic tracking of 3D human figures using 2D image motion. ECCV (pp. 702--718). Part II.

Digital Library

[13]

Stitson, M. O., Gammerman, A., Vapnik, V., Vovk, V., Watkins, C., & Weston, J. (1998). Support vector regression with ANOVA decomposition kernels. In B. Schöölkopf, C. J. C. Burges and A. J. Smola (Eds.), Advances in kernel methods: Support vector learning. The MIT Press.

Digital Library

[14]

Tenenbaum, J. B., & Freeman, W. T. (2000). Separating style and content with bilinear models. Neural Computation, 12, 1247--1283.

Digital Library

[15]

Urtasun, R., Fleet, D. J., & Fua, P. (2006a). 3D people tracking with Gaussian process dynamical models. IEEE Conf. Comp. Vis. & Pattern Rec. (pp. 238--245). Vol. I.

Digital Library

[16]

Urtasun, R., Fleet, D. J., & Fua, P. (2006b). Temporal motion models for monocular and multiview 3D human body tracking. CVIU, 104, 157--177.

Digital Library

[17]

Urtasun, R., Fleet, D. J., Hertzmann, A., & Fua, P. (2005). Priors for people tracking from small training sets. IEEE Inter. Conf. Comp. Vis. (ICCV) (pp. 403--410). Vol. 1.

Digital Library

[18]

Vasilescu, M. A. O. (2002). Human motion signatures: Analysis, synthesis, recognition. Inter. Conf. Pattern Recognition (ICPR) (pp. 456--460). Vol. III.

Digital Library

[19]

Vasilescu, M. A. O., & Terzopoulos, D. (2002). Multilinear analysis of image ensembles: TensorFaces. Computer Vision - ECCV 2002 (pp. 447--460). Springer. Part I.

Digital Library

[20]

Vasilescu, M. A. O., & Terzopoulos, D. (2004). TensorTextures: Multilinear image-based rendering. ACM Transactions on Graphics, 23, 336--342. Proc. SIGGRAPH.

Digital Library

[21]

Vlasic, D., Brand, M., Pfister, H., & Popovi&cacute;ć, J. (2005). Face transfer with multilinear models. ACM Transactions on Graphics, 24, 426--433. Proc. SIGGRAPH.

Digital Library

[22]

Wang, J. M., Fleet, D. J., & Hertzmann, A. (2006). Gaussian process dynamical models. Adv. Neural Information Processing Systems 18 (pp. 1441--1448). Proc. NIPS '05.

[23]

Zhu, C., Byrd, R. H., Lu, P., & Nocedal, J. (1997). Algorithm 778: L-BFGS-B: Fortran subroutines for large-scale bound-constrained optimization. ACM Transactions on Mathematical Software, 23, 550--560.

Digital Library

Cited By

Jang DYe YWon JLee S(2023)MOCHA: Real-Time Motion Characterization via Context MatchingSIGGRAPH Asia 2023 Conference Papers10.1145/3610548.3618252(1-11)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.1145/3610548.3618252
Tang XWu LWang HHu BGong XLiao YLi SKou QJin X(2023)RSMT: Real-time Stylized Motion Transition for CharactersACM SIGGRAPH 2023 Conference Proceedings10.1145/3588432.3591514(1-10)Online publication date: 23-Jul-2023
https://dl.acm.org/doi/10.1145/3588432.3591514
Kim CEom HYoo JChoi SNoh J(2023)Interactive Locomotion Style Control for a Human Character based on Gait Cycle FeaturesComputer Graphics Forum10.1111/cgf.1498843:1Online publication date: 18-Oct-2023
https://doi.org/10.1111/cgf.14988
Show More Cited By

Multifactor Gaussian process models for style-content separation
1. Computing methodologies

Recommendations

Overdetermined blind source separation by gaussian mixture model
ICIC'11: Proceedings of the 7th international conference on Advanced Intelligent Computing Theories and Applications: with aspects of artificial intelligence

The blind separation of overdetermined mixtures, i.e., the case where more sensors than sources are available is considered in this paper. The contrast function for overdetermined blind source separation problem is presented, together with its gradient. ...
Source Separation with Gaussian Process Models
ECML '07: Proceedings of the 18th European conference on Machine Learning

In this paper we address a method of source separation in the case where sources have certain temporal structures. The key contribution in this paper is to incorporate Gaussian process (GP) model into source separation, representing the latent function ...
Dirichlet process Gaussian mixture models: choice of the base distribution

In the Bayesian mixture modeling framework it is possible to infer the necessary number of components to model the data and therefore it is unnecessary to explicitly restrict the number of components. Nonparametric mixture models sidestep the problem of ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

ICML '07: Proceedings of the 24th international conference on Machine learning

June 2007

1233 pages

ISBN:9781595937933

DOI:10.1145/1273496

Editor:
Zoubin Ghahramani
University of Cambridge, United Kingdom

Copyright © 2007 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Machine Learning Journal

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 20 June 2007

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Qualifiers

Article

Conference

ICML '07 & ILP '07

Sponsor:

ICML '07 & ILP '07: The 24th Annual International Conference on Machine Learning held in conjunction with the 2007 International Conference on Inductive Logic Programming

June 20 - 24, 2007

Oregon, Corvalis, USA

Acceptance Rates

Overall Acceptance Rate 140 of 548 submissions, 26%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

95
Total Citations
View Citations
493
Total Downloads

Downloads (Last 12 months)4
Downloads (Last 6 weeks)0

Reflects downloads up to 18 Aug 2024

Other Metrics

View Author Metrics

Citations

Cited By

Jang DYe YWon JLee S(2023)MOCHA: Real-Time Motion Characterization via Context MatchingSIGGRAPH Asia 2023 Conference Papers10.1145/3610548.3618252(1-11)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.1145/3610548.3618252
Tang XWu LWang HHu BGong XLiao YLi SKou QJin X(2023)RSMT: Real-time Stylized Motion Transition for CharactersACM SIGGRAPH 2023 Conference Proceedings10.1145/3588432.3591514(1-10)Online publication date: 23-Jul-2023
https://dl.acm.org/doi/10.1145/3588432.3591514
Kim CEom HYoo JChoi SNoh J(2023)Interactive Locomotion Style Control for a Human Character based on Gait Cycle FeaturesComputer Graphics Forum10.1111/cgf.1498843:1Online publication date: 18-Oct-2023
https://doi.org/10.1111/cgf.14988
Song WJin XLi SChen CHao AHou X(2023)FineStyle: Semantic-Aware Fine-Grained Motion Style Transfer with Dual Interactive-Flow FusionIEEE Transactions on Visualization and Computer Graphics10.1109/TVCG.2023.332021629:11(4361-4371)Online publication date: 1-Nov-2023
https://dl.acm.org/doi/10.1109/TVCG.2023.3320216
Ma LYang ZTong XGuo BYin K(2021)Learning and Exploring Motor Skills with Spacetime BoundsComputer Graphics Forum10.1111/cgf.14263040:2(251-263)Online publication date: 4-Jun-2021
https://doi.org/10.1111/cgf.142630
Ribet SWannous HVandeborre J(2021)Survey on Style in 3D Human Body Motion: Taxonomy, Data, Recognition and Its ApplicationsIEEE Transactions on Affective Computing10.1109/TAFFC.2019.290616712:4(928-948)Online publication date: 1-Oct-2021
https://doi.org/10.1109/TAFFC.2019.2906167
Carlisi CReed KHelmink FLachlan RCosker DViding EMareschal I(2021)Using genetic algorithms to uncover individual differences in how humans represent facial emotionRoyal Society Open Science10.1098/rsos.2022518:10Online publication date: 13-Oct-2021
https://doi.org/10.1098/rsos.202251
Su YZhang JXing MPeng WFeng Z(2021)Disentangling style on dynamic aligned poses for individual identificationAd Hoc Networks10.1016/j.adhoc.2020.102384113(102384)Online publication date: Mar-2021
https://doi.org/10.1016/j.adhoc.2020.102384
Zhu HLuo MWang RZheng AHe R(2021)Deep Audio-visual Learning: A SurveyInternational Journal of Automation and Computing10.1007/s11633-021-1293-018:3(351-376)Online publication date: 1-Jun-2021
https://dl.acm.org/doi/10.1007/s11633-021-1293-0
Dong YAristidou AShamir AMahler MJain E(2020)Adult2child: Motion Style Transfer using CycleGANsProceedings of the 13th ACM SIGGRAPH Conference on Motion, Interaction and Games10.1145/3424636.3426909(1-11)Online publication date: 16-Oct-2020
https://dl.acm.org/doi/10.1145/3424636.3426909
Show More Cited By

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents