Generalized Laplacian Eigenmaps for Modeling and Tracking Human Motions

  title={Generalized Laplacian Eigenmaps for Modeling and Tracking Human Motions},
  author={J. M. D. Rinc{\'o}n and Michal Lewandowski and Jean-Christophe Nebel and D. Makris},
  journal={IEEE Transactions on Cybernetics},
This paper presents generalized Laplacian eigenmaps, a novel dimensionality reduction approach designed to address stylistic variations in time series. It generates compact and coherent continuous spaces whose geometry is data-driven. This paper also introduces graph-based particle filter, a novel methodology conceived for efficient tracking in low dimensional space derived from a spectral dimensionality reduction method. Its strengths are a propagation scheme, which facilitates the prediction… Expand
Multilayer Joint Gait-Pose Manifolds for Human Gait Motion Modeling
The experimental results on the Carnegie Mellon University motion capture data demonstrate the advantages of the proposed multilayer models over several existing GP-based motion models in terms of the overall performance of human gait motion modeling. Expand
Video-Based Human Walking Estimation Using Joint Gait and Pose Manifolds
The idea of joint gait-pose manifold (JGPM) is proposed, which represents gait kinematics by coupling two nonlinear variables, pose and gait in a unified latent space, which extends the Gaussian process latent variable model for JGPM learning. Expand
Deep Learning Frameworks for Human Motion Analysis
The human body is a complex structure consisting of multiple organs, muscles and bones. However, in regard to modeling human motion, the information about fixed set of joint locations (with fixedExpand
GlocalNet: Class-aware Long-term Human Motion Synthesis
A two-stage activity generation method to achieve long-term human motion synthesis by learning to synthesize a sparse motion trajectory and demonstrating the superiority of the proposed method over SOTA methods using various quantitative evaluation metrics on publicly available datasets. Expand
1D representation of Laplacian eigenmaps and dual k-nearest neighbours for unified video coding
It is evaluated by simulation experiments that the proposed framework of video coding based on Laplacian eigenmaps can attain better performance of BPP and PSNR than that of the state-of-the-art methods, such as highly efficient video coding. Expand
Nonlinear model reduction of the Navier-Stokes-Equations
  • Lorenz Pyta, D. Abel
  • Mathematics, Computer Science
  • 2016 American Control Conference (ACC)
  • 2016
In this paper three different methods for nonlinear dimensionality reduction are examined: Sammon mapping, Laplacian eigenmaps and autoencoder. These are extended such that they fit in the frameworkExpand
Sparse representation and dictionary learning for biometrics and object tracking
A fully automated system for recognition from ear images based upon sparse representation, gender classification and object tracking, and a robust tracking system based on adaptive sparse representation and feedback are presented. Expand
Manifold Learning and Spectral Clustering for Image Phylogeny Forests
The combination of manifold learning and spectral clustering approaches, which have been successfully used in different applications embedding the original data into a lower, but meaningful, dimensional space, are proposed. Expand
Full body human motion estimation on lie groups using 3D marker position measurements
The results show that the proposed filter significantly outperforms the Euler angles based EKF, since it estimates human motion more accurately and is not affected by gimbal lock. Expand
Collective Representation for Abnormal Event Detection
This paper proposes a robust collective representation with multi-feature descriptors for abnormal event detection, and builds the intrinsic relation between different feature descriptors and capture concept drift in the video sequence which can robustly discriminate between abnormal events and normal events. Expand


Temporal Extension of Laplacian Eigenmaps for Unsupervised Dimensionality Reduction of Time Series
A novel non-linear dimensionality reduction method, called Temporal Laplacian Eigenmaps, is introduced to process efficiently time series data and its lower computational cost and generalisation abilities suggest it is scalable to larger datasets. Expand
People Tracking with the Laplacian Eigenmaps Latent Variable Model
It is demonstrated that LELVM not only provides sufficient constraints for robust operation in the presence of missing, noisy and ambiguous image measurements, but also compares favorably with alternative trackers based on PCA or GPLVM priors. Expand
Multifactor Gaussian process models for style-content separation
This work proposes a generalization of multilinear models using nonlinear basis functions and obtains a multifactor form of the Gaussian process latent variable model, in which each factor is kernelized independently, allowing nonlinear mappings from any particular factor to the data. Expand
Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering
The algorithm provides a computationally efficient approach to nonlinear dimensionality reduction that has locality preserving properties and a natural connection to clustering. Expand
The Laplacian Eigenmaps Latent Variable Model
We introduce the Laplacian Eigenmaps Latent Variable Model (LELVM), a probabilistic method for nonlinear dimensionality reduction that combines the advantages of spectral methods—global optimisationExpand
Separating style and content on a nonlinear manifold
Bilinear and multi-linear models have been successful in decomposing static image ensembles into perceptually orthogonal sources of variations, e.g., separation of style and content. If we considerExpand
Priors for people tracking from small training sets
It is shown that the SGPLVM sufficiently constrains the problem such that tracking can be accomplished with straightforward deterministic optimization. Expand
Monocular Tracking of 3D Human Motion with a Coordinated Mixture of Factor Analyzers
Quantitative comparisons show that the formulation produces more accurate 3D pose estimates over time than those that can be obtained via a number of previously-proposed particle filtering based tracking algorithms. Expand
Advanced non linear dimensionality reduction methods for multidimensional time series : applications to human motion analysis
Two variants of temporally constrained human motion descriptors are proposed, which become a foundation of view independent action recognition frameworks, and demonstrate excellent robustness against style, view, and speed variability in recognition of different kinds of motions. Expand
Multi-activity Tracking in LLE Body Pose Space
The dynamical model helps to track through poorly segmented low-resolution image sequences where tracking otherwise fails, while at the same time reliably classifying the activity type, and is evaluated on challenging sequences with subjects that are alternating between running and walking movements. Expand