Gaussian process latent variable models for human pose estimation

Gaussian process latent variable models for human pose estimation

We describe a method for recovering 3D human body pose from silhouettes. Our model is based on learning a latent space using the Gaussian Process Latent Variable Model (GP-LVM) [1] encapsulating both pose and silhouette features Our method is generative, this allows us to model the ambiguities of a...

Fuld beskrivelse

Bibliografiske detaljer
Main Authors:	Ek, CH, Torr, PHS, Lawrence, ND
Format:	Conference item
Sprog:	English
Udgivet:	Springer 2008

Lignende værker

Ambiguity modeling in latent spaces
af: Ek, CH, et al.
Udgivet: (2008)

PoseField: an efficient mean-field based method for joint estimation of human pose, segmentation, and depth
af: Vineet, V, et al.
Udgivet: (2013)

Surface Approximation by Means of Gaussian Process Latent Variable Models and Line Element Geometry
af: Ivan De Boi, et al.
Udgivet: (2023-01-01)

Simultaneous segmentation and pose estimation of humans using dynamic graph cuts
af: Kohli, P, et al.
Udgivet: (2008)

Discriminative Gaussian Process Latent Variable Model for Classification
af: Urtasun, Raquel, et al.
Udgivet: (2007)

POSECUT: simultaneous segmentation and 3d pose estimation of humans using dynamic graph-cuts
af: Bray, M, et al.
Udgivet: (2006)

Hand pose estimation using hierarchical detection
af: Stenger, B, et al.
Udgivet: (2004)

A Gaussian Process Latent Variable Model for Subspace Clustering
af: Shangfang Li
Udgivet: (2021-01-01)

Pose estimation and tracking using multivariate regression
af: Thayananthan, A, et al.
Udgivet: (2008)

Randomized trees for human pose detection
af: Rogez, G, et al.
Udgivet: (2008)

Estimating 3D hand pose using hierarchical multi-label classification
af: Stenger, B, et al.
Udgivet: (2006)

Distributed variational inference in sparse Gaussian process regression and latent variable models
af: Gal, Y
Udgivet: (2014)

Latent SVMs for human detection with a locally affine deformation field
af: Ladický, L, et al.
Udgivet: (2012)

Fast human pose detection using randomized hierarchical cascades of rejectors
af: Rogez, G, et al.
Udgivet: (2012)

Vision-Based Satellite Recognition and Pose Estimation Using Gaussian Process Regression
af: Haopeng Zhang, et al.
Udgivet: (2019-01-01)

Multi-Modal Gaussian Process Latent Variable Model With Semi-Supervised Label Dequantization
af: Keisuke Maeda, et al.
Udgivet: (2024-01-01)

Hierarchical part-based human body pose estimation
af: Navaratnam, R, et al.
Udgivet: (2005)

Deep fully-connected part-based models for human pose estimation
af: De Bem, R, et al.
Udgivet: (2018)

3D hand shape and pose from images in the wild
af: Boukhayma, A, et al.
Udgivet: (2020)

Gaussian Processes Proxy Model with Latent Variable Models and Variogram-Based Sensitivity Analysis for Assisted History Matching
af: Dongmei Zhang, et al.
Udgivet: (2020-08-01)

Graphical model selection for Gaussian conditional random fields in the presence of latent variables
af: Frot, B, et al.
Udgivet: (2018)

Bayesian model estimation and selection for epipolar geometry and generic manifold fitting
af: Torr, PHS
Udgivet: (2002)

Bipartite graph reasoning GANs for person pose and facial image synthesis
af: Tang, H, et al.
Udgivet: (2022)

Transferring Nonlinear Representations using Gaussian Processes with a Shared Latent Space
af: Urtasun, Raquel, et al.
Udgivet: (2008)

Real-time RGB-D camera pose estimation in novel scenes using a relocalisation cascade
af: Cavallari, T, et al.
Udgivet: (2019)

Real-time RGB-D camera pose estimation in novel scenes using a relocalisation cascade
af: Cavallari, T, et al.
Udgivet: (2018)

Exploring Rare Pose in Human Pose Estimation
af: Jihye Hwang, et al.
Udgivet: (2020-01-01)

Human pose estimation using a joint pixel-wise and part-wise formulation
af: Ladický, L, et al.
Udgivet: (2015)

Linear non-Gaussian acyclic models for causal inference of latent variables in structural equation model
af: Luk, Chun To
Udgivet: (2023)

PosturePose: Optimized Posture Analysis for Semi-Supervised Monocular 3D Human Pose Estimation
af: Lawrence Amadi, et al.
Udgivet: (2023-12-01)

The Progress of Human Pose Estimation: A Survey and Taxonomy of Models Applied in 2D Human Pose Estimation
af: Tewodros Legesse Munea, et al.
Udgivet: (2020-01-01)

Calibrating cardiac electrophysiology models using latent Gaussian processes on atrial manifolds
af: Sam Coveney, et al.
Udgivet: (2022-10-01)

Recurrent human pose estimation
af: Belagiannis, V, et al.
Udgivet: (2016)

Recurrent human pose estimation
af: Belagiannis, V, et al.
Udgivet: (2017)

Learning Gaussian Graphical Models with Observed or Latent FVSs
af: Liu, Ying, et al.
Udgivet: (2015)

Improved initialization and Gaussian mixture pairwise terms for dense random fields with mean-field inference
af: Vineet, V, et al.
Udgivet: (2012)

Collaborative large-scale dense 3D reconstruction with online inter-agent pose optimisation
af: Golodetz, S, et al.
Udgivet: (2018)

A Grasp-Pose Generation Method Based on Gaussian Mixture Models
af: Wenjia Wu
Udgivet: (2015-11-01)

MLESAC: a new robust estimator with application to estimating image geometry
af: Torr, PHS, et al.
Udgivet: (2000)

Graphical model selection for gaussian conditional random fields in the presence of latent variables: theory and application to genetics
af: Frot, B
Udgivet: (2016)