Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 1,517

The DOI matches its Crossref record.

Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group

Vemulapalli, Raviteja, Arrate, Felipe, Chellappa, Rama·2014·2014 IEEE Conference on Computer Vision and Pattern Recognition
DOI 10.1109/cvpr.2014.82
Open this paper in CoChat — free account

Abstract

Recently introduced cost-effective depth sensors coupled with the real-time skeleton estimation algorithm of Shotton et al. [16] have generated a renewed interest in skeleton-based human action recognition. Most of the existing skeleton-based approaches use either the joint locations or the joint angles to represent a human skeleton. In this paper, we propose a new skeletal representation that explicitly models the 3D geometric relationships between various body parts using rotations and translations in 3D space. Since 3D rigid body motions are members of the special Euclidean group SE(3), the proposed skeletal representation lies in the Lie group SE(3)×.. .×SE(3), which is a curved manifold. Using the proposed representation, human actions can be modeled as curves in this Lie group. Since classification of curves in this Lie group is not an easy task, we map the action curves from the Lie group to its Lie algebra, which is a vector space. We then perform classification using a combination of dynamic time warping, Fourier temporal pyramid representation and linear SVM. Experimental results on three action datasets show that the proposed representation performs better than many existing skeletal representations. The proposed approach also outperforms various state-of-the-art skeleton-based human action recognition approaches.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr.2014.82

Cites

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

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

No references could be resolved yet.

Research works printed but not linked: 27

  1. wang, 2012, Mining actionlet ensemble for action recognition with depth cameras, CVPR
  2. 10.1109/TIP.2009.2017143 · DOI
  3. 10.1109/CVPR.2013.123 · DOI · Paper page
  4. 10.1109/ICCV.2005.90 · DOI
  5. 10.1109/CVPR.2011.5995316 · DOI · Paper page
  6. 10.1109/CVPRW.2013.76 · DOI · Paper page
  7. 10.1109/CVPRW.2013.77 · DOI
  8. murray, 1994, A Mathematical Introduction to Robotic Manipulation
  9. 10.1109/CVPRW.2012.6239231 · DOI
  10. 10.1109/ICCV.1998.710709 · DOI
  11. 10.1109/CVPRW.2012.6239233 · DOI · Paper page
  12. yang, 2012, EigenJoints-based action recognition using n�ive-bayes-nearest-neighbor, cvprw
  13. 10.1007/978-3-642-44964-2_8 · DOI
  14. zatsiorsky, 1997, Kinematics of Human Motion
  15. 10.1109/ROBOT.1998.680708 · DOI
  16. zefran, 1996, Choice of riemannian metrics for rigid body kinematics, ASME Design Engineering Technical Conference and Computers in Engineering Conference
  17. 10.1109/CVPRW.2013.78 · DOI
  18. gavrila, 1995, Towards 3-D model-based tracking and recognition of human movement: A multiview approach, International workshop on Automatic Face and Gesture Recognition
  19. 10.1109/CVPRW.2013.153 · DOI
  20. 10.1007/978-3-540-74048-3 · DOI · Paper page
  21. 10.1145/1922649.1922653 · DOI · Paper page
  22. 10.1109/CVPRW.2010.5543273 · DOI · Paper page
  23. 10.3758/BF03212378 · DOI · Paper page
  24. hussein, 2013, Human action recognition using a temporal hierarchy of co-variance descriptors on 3D joint locations, IJCAI
  25. hall, 2003, Lie Groups Lie Algebras and Representations An Elementary Introduction, 10.1007/978-0-387-21554-9 · DOI · Paper page
  26. 10.1016/j.cviu.2006.08.002 · DOI · Paper page
  27. lv, 2006, Recognition and segmentation of 3D human action using HMM and multi-class adaboost, ECCV

Cited by

Metadata

Authors
Vemulapalli, R., Arrate, F., & Chellappa, R.
Venue
2014 IEEE Conference on Computer Vision and Pattern Recognition
Publisher
IEEE
Published
2014-06
Pages
588-595
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr.2014.82
OpenAlex
W2048821851
Cited by
1,517
References
0
FWCI
58.38
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.