Dynamical binary latent variable models for 3D human pose tracking
The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
We introduce a new class of probabilistic latent variable model called the Implicit Mixture of Conditional Restricted Boltzmann Machines (imCRBM) for use in human pose tracking. Key properties of the imCRBM are as follows: (1) learning is linear in the number of training exemplars so it can be learned from large datasets; (2) it learns coherent models of multiple activities; (3) it automatically discovers atomic “movemes” and (4) it can infer transitions between activities, even when such transitions are not present in the training set. We describe the model and how it is learned and we demonstrate its use in the context of Bayesian filtering for multi-view and monocular pose tracking. The model handles difficult scenarios including multiple activities and transitions among activities. We report state-of-the-art results on the HumanEva dataset.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
CONDENSATION—Conditional Density Propagation for Visual Tracking
Isard, M., & Blake, A. (1998) · International Journal of Computer Vision · doi:10.1023/a:1008078328650 · Cited by 4,886 · cited 1×
“This, however, can easily be addressed within the context of a particle filter, by defining an augmented state [ 7 ] ^t = xt N:t, and a transition density that (1) temporally shifts the elements of augmented state by one (dropping the oldest state in the sequence) and (2) predicts the most recent state according to th…”
BackgroundTraining Products of Experts by Minimizing Contrastive Divergence
Hinton, G. E. (2002) · Neural Computation · doi:10.1162/089976602760128018 · Cited by 4,879 · cited 1×
“…likelihood, p(x t |x ht ), over parameters θ = {W, A, B, c, d} but this is difficult for all but the smallest models due to the intractability of computing Z. Learning , however, still works well if we approximately follow the gradient of another function called the contrastive divergence (CD) [6].”
BackgroundSelf-citationTopologically-constrained latent variable models
Urtasun, R., Fleet, D. J., Geiger, A., Popović, J., Darrell, T. J., & Lawrence, N. D. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390292 · Cited by 125 · cited 2×
“[25]).”
MethodSelf-citation
Cited by
Structural-RNN: Deep Learning on Spatio-Temporal Graphs
Jain, A., Zamir, A. R., Savarese, S., & Saxena, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.573 · Cited by 1,133
“Several approaches based on Gaussian processes [59, 63], Restricted Boltzmann Machines (RBMs) [57, 56, 51], and RNNs [14] have been proposed to model human motion.”
BackgroundMethodRecurrent Network Models for Human Dynamics
Fragkiadaki, K., Levine, S., Felsen, P., & Malik, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.494 · Cited by 860
3D Human Pose Estimation from Monocular Images with Deep Convolutional Neural Network
Li, S., & Chan, A. B. (2015) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-16808-1_23 · Cited by 443
3D Human Pose Estimation from a Single Image via Distance Matrix Regression
Moreno-Noguer, F. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.170 · Cited by 397
3D Human pose estimation: A review of the literature and analysis of covariates
Sarafianos, N., Boteanu, B., Ionescu, B., & Kakadiaris, I. A. (2016) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2016.09.002 · Cited by 323
Adversarial Geometry-Aware Human Motion Prediction
Gui, L.-Y., Wang, Y.-X., Liang, X., & Moura, J. M. F. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01225-0_48 · Cited by 276
Kimera: From SLAM to spatial perception with 3D dynamic scene graphs
Rosinol, A., Violette, A., Abate, M., Hughes, N., Chang, Y., Shi, J., Gupta, A., & Carlone, L. (2021) · The International Journal of Robotics Research · doi:10.1177/02783649211056674 · Cited by 271
3D Pictorial Structures for Multiple Human Pose Estimation
Belagiannis, V., Amin, S., Andriluka, M., Schiele, B., Navab, N., & Ilic, S. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.216 · Cited by 258
Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images
Watter, M., Springenberg, J. T., Boedecker, J., & Riedmiller, M. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.07365 · Cited by 212
“Second, learning relations between pairs of images – although without control – has received considerable attention from the community during the last years [31, 32].”
BackgroundDeep adaptive feature embedding with local sample distributions for person re-identification
Wu, L., Wang, Y., Gao, J., & Li, X. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2017.08.029 · Cited by 170
“The deep network of CDBN is optimized on a single GPU GTX 980 using the code provided by [75] (1).”
MethodA Deep Learning Method Combined Sparse Autoencoder with SVM
Ju, Y., Guo, J., & Liu, S. (2015) · 2015 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery · doi:10.1109/cyberc.2015.39 · Cited by 37
Metadata
- Authors
- Taylor, G. W., Sigal, L., Fleet, D. J., & Hinton, G. E.
- Venue
- 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
- Publisher
- IEEE
- Published
- 2010-06
- Pages
- 631-638
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2034792058
- Cited by
- 140
- References
- 3
- FWCI
- 10.17
- Type
- conference paper
- Language
- en
- Open access
- closed
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.