The DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Topologically-constrained latent variable models
Abstract
In dimensionality reduction approaches, the data are typically embedded in a Euclidean latent space. However for some data sets this is inappropriate. For example, in human motion data we expect latent spaces that are cylindrical or a toroidal, that are poorly captured with a Euclidean space. In this paper, we present a range of approaches for embedding data in a non-Euclidean latent space. Our focus is the Gaussian Process latent variable model. In the context of human motion modeling this allows us to (a) learn models with interpretable latent directions enabling, for example, style/content separation, and (b) generalise beyond the data set enabling us to learn transitions between motion styles even though such transitions are not present in the data.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Spatio-temporal graphs (st-graphs) are a popular [39,37,4,11,32,65,22] general tool for representing such high-level spatio-temporal structures.”
From Structural-RNN: Deep Learning on Spatio-Temporal Graphs (2016) · cites this paper as [32]
Citations
Cites
Nonlinear Dimensionality Reduction by Locally Linear Embedding
Roweis, S. T., & Saul, L. K. (2000) · Science · doi:10.1126/science.290.5500.2323 · Cited by 14,965
A Global Geometric Framework for Nonlinear Dimensionality Reduction
Tenenbaum, J. B., Silva, V. D., & Langford, J. C. (2000) · Science · doi:10.1126/science.290.5500.2319 · Cited by 13,585
Kovar, L., Gleicher, M. L., & Pighin, F. P. (2008) · ACM SIGGRAPH Courses · doi:10.1145/1401132.1401202 · Cited by 1,073
Gaussian Process Dynamical Models for Human Motion
Wang, J. M., Fleet, D. J., & Hertzmann, A. (2007) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.1167 · Cited by 1,046
Self-citationProbabilistic Non-linear Principal Component Analysis with Gaussian Process Latent Variable Models
Lawrence, N. D. (2005) · Cited by 906
Self-citationStyle-based inverse kinematics
Grochow, K., Martin, S. L., Hertzmann, A., & Popović, Z. (2004) · ACM Transactions on Graphics · doi:10.1145/1015706.1015755 · Cited by 650
Learning a kernel matrix for nonlinear dimensionality reduction
Weinberger, K. Q., Sha, F., & Saul, L. K. (2004) · doi:10.1145/1015330.1015345 · Cited by 526
3D People Tracking with Gaussian Process Dynamical Models
Urtasun, R., Fleet, D. J., & Fua, P. (2006) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2006.15 · Cited by 444
Self-citationInferring 3D body pose from silhouettes using activity manifold learning
Elgammal, A., & Lee, C.-S. (2004) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2004.1315230 · Cited by 421
Gaussian Process Dynamical Models
Wang, J., Hertzmann, A., & Blei, D. M. (2005) · Cited by 418
Cited by
Sorted by citations
Items 101–125 of 125
Isometric Gaussian Process Latent Variable Model for Dissimilarity DataPreprint
Jørgensen, M., & Hauberg, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.11741 · Cited by 3
Spatial–Temporal Attention-Based Human Dynamics Retrospection
Dong, M., & Xu, C. (2019) · IEEE Access · doi:10.1109/access.2019.2933221 · Cited by 2
Real-Time Cleaning and Refinement of Facial Animation Signals
Berson, E., Soladié, C., & Stoiber, N. (2020) · International Conference on Graphics and Signal Processing (ICGSP) · doi:10.1145/3406971.3406985 · Cited by 3
Summarizing Data Structures with Gaussian Process and Robust Neighborhood Preservation
Watanabe, K., Maeda, K., Ogawa, T., & Haseyama, M. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-26419-1_10 · Cited by 2
Intention Inference and Decision Making with Hierarchical Gaussian Process Dynamics Models
Wang, Z. (2013) · Technischen Universität Darmstadt · doi:10.26083/tuprints-00003617 · Cited by 2
Locomotion synthesis methods for humanoid characters
Wang, J. M. (2010) · TSpace (University of Toronto) · Cited by 2
Probabilistic Feature Extraction from Multivariate Time Series Using Spatio-Temporal Constraints
Lewandowski, M., Makris, D., & Nebel, J. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-20847-8_15 · Cited by 1
Two-layer dual gait generative models for human motion estimation from a single camera
Zhang, X., Fan, G., & Chou, L. (2012) · Image and Vision Computing · doi:10.1016/j.imavis.2012.12.001 · Cited by 1
High-dimensional Motion Planning using Latent Variable Models via Approximate Inference.
Ha, J.-S., Chae, H.-J., & Han-lim Choi, A. (2017) · Cited by 1
Motion Editing for Quadruped Characters via Latent Frequency Embedding
Zeng, R., Pan, J., Dai, J. P., Gao, Y., Bai, J., & Qin, H. (2024) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2024.3507952 · Cited by 1
Human pose estimation using motion priors and ensemble models
Ukita, N. (2017) · International Conference on Advanced Computer Science and Information Systems · doi:10.1109/icacsis.2017.8355005 · Cited by 1
Conditional Neural Relational Inference for Interacting Systems
Ramos, J. A. C., Blondé, L., Armand, S., & Kalousis, A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86517-7_12 · Cited by 2
3D Motion Data aided Human Action Recognition and Pose Estimation
Gong, W. (2013) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · Cited by 1
Structure-Aware Human-Action GenerationPreprint
Yu, P., Zhao, Y., Li, C., Yuan, J., & Chen, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.01971 · Cited by 1
Efficient 3D Upper Body Tracking with Self-Occlusions
Chen, J., & Ji, Q. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.887
Gaussian Process-based Manifold Learning for Human Motion Modeling
Fan, G., & Zhang, X. (2012) · IGI Global eBooks · doi:10.4018/978-1-4666-1806-0.ch015
Learning From Natural Human Interactions For Assistive Robots
Jain, A. (2016) · eCommons (Cornell University) · doi:10.7298/x4mw2f2v
Perceptual Facial Expression Representation
Mikheeva, O., Ek, C. H., & Kjellström, H. (2018) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg.2018.00035
Approximate Inference for Multiplicative Latent Force ModelsPreprint
Tait, D. J., & Worton, B. J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.11755
Mapping Grasping Motion of Hand between Master and Slave in a Low-Dimensional Latent Space
Guo, C., Liu, Y., Matsuzaka, A., Shirato, T., Namiki, A., & Mouri, T. (2018) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2018.8665271
Choreography Composed by Deep Learning
Suzuki, R., & Ochiai, Y. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-78642-7_73
Observable subspaces for 3D human motion recovery
Fossati, A., Salzmann, M., & Fua, P. (2009) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvprw.2009.5206489
Transfer Learning for Human Motion Prediction: Improving Accuracy Under Data Scarcity
Casarin, M., Vanuzzo, M., Guidolin, M., Reggiani, M., & Michieletto, S. (2026) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2026.3670340
Leveraging Neural Networks for 3D Facial Animation Editing
Berson, E. (2021) · theses.fr (ABES) · doi:10.70675/ada96a82zfc55z4ec5z890ezec13d5d5af28
UniMiB SHAR: A Dataset for Human Activity Recognition Using Acceleration Data from Smartphones
Micucci, D., Mobilio, M., & Napoletano, P. (2017) · doi:10.20944/preprints201706.0033.v1 · Cited by 596
“[16] are some examples of methods for learning dynamical models of human motion from camera data.”
Method
Metadata
- Authors
- Urtasun, R., Fleet, D. J., Geiger, A., Popović, J., Darrell, T. J., & Lawrence, N. D.
- Affiliations
- MIT Computer Science and Artificial Intelligence Laboratory (US)
- University of Toronto (CA)
- Karlsruhe Institute of Technology (DE)
- University of Manchester (GB)
- Venue
- Proceedings of the 25th international conference on Machine learning - ICML '08
- Publisher
- ACM Press
- Published
- 2008
- Pages
- 1080-1087
- OpenAlex
- W2171461439
- Cited by
- 125
- References
- 12
- Citations by year
- 2026: 1 · 2025: 1 · 2024: 2 · 2023: 4 · 2022: 3 · 2021: 6 · 2020: 8 · 2019: 7 · 2018: 7 · 2017: 8 · 2016: 3 · 2015: 8 · 2014: 7 · 2013: 13 · 2012: 11
- FWCI
- 8.90
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Machine Learning (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Gaussian Processes and Bayesian Inference
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Human Motion and Animation
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Keywords
- Gaussian process latent variable model, dimensionality reduction, human motion modeling
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
