Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 213

The DOI matches its Crossref record.

Rolling Rotations for Recognizing Human Actions from 3D Skeletal Data

Vemulapalli, Raviteja, Chellappa, Rama·2016·2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Abstract

Recently, skeleton-based human action recognition has been receiving significant attention from various research communities due to the availability of depth sensors and real-time depth-based 3D skeleton estimation algorithms. In this work, we use rolling maps for recognizing human actions from 3D skeletal data. The rolling map is a well-defined mathematical concept that has not been explored much by the vision community. First, we represent each skeleton using the relative 3D rotations between various body parts. Since 3D rotations are members of the special orthogonal group SO3, our skeletal representation becomes a point in the Lie group SO3× ... × SO3, which is also a Riemannian manifold. Then, using this representation, we model human actions as curves in this Lie group. Since classification of curves in this non-Euclidean space is a difficult task, we unwrap the action curves onto the Lie algebra so3× ... × so3(which is a vector space) by combining the logarithm map with rolling maps, and perform classification in the Lie algebra. Experimental results on three action datasets show that the proposed approach performs equally well or better when compared to state-of-the-art.

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.2016.484

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: 38

  1. yang, 2012, Eigen Joints-based Action Recognition Using Naive-Bayes-Nearest-Neighbor, CVPR Workshops
  2. 10.1109/CVPR.2012.6247813 · DOI · Paper page
  3. 10.1109/CVPR.2014.82 · DOI · Paper page
  4. 10.1111/j.1467-8659.2009.01375.x · doi:10.1111/j.1467-8659.2009.01375.x
  5. sung, 2012, Unstructured Human Activity Detection from RGBD Images, ICRA
  6. 10.1109/ICCV.1998.710709 · DOI
  7. 10.1109/CVPRW.2012.6239233 · DOI · Paper page
  8. 10.1109/ICCV.2013.389 · DOI
  9. 10.1109/ICCV.2013.334 · DOI
  10. hüper, 2002, Smoothing Interpolation Curves on Manifolds with Applications to Path Planning, Mediter-ranean Conference on Control and Automation
  11. 10.1007/s10883-007-9027-3 · doi:10.1007/s10883-007-9027-3
  12. hussein, 2013, Human Action Recognition Using a Temporal Hierarchy of Covariance Descriptors on 3D Joint Locations, IJCAI
  13. 10.1007/s10851-009-0161-2 · DOI · Paper page
  14. 10.1109/TCSVT.2011.2181452 · DOI
  15. lv, 2006, Recognition and Segmentation of 3D Human Action Using HMM and Multi-class Adaboost, ECCV
  16. 10.1109/ICPR.2014.340 · doi:10.1109/icpr.2014.340
  17. 10.1109/CVPRW.2012.6239231 · DOI
  18. 10.1109/CVPRW.2013.76 · DOI · Paper page
  19. 10.1109/CVPR.2013.98 · DOI · Paper page
  20. 10.1109/TPAMI.2010.184 · DOI · Paper page
  21. caseiro, 2013, Rolling Riemannian Manifolds to Solve the Multiclass Classification Problem, CVPR
  22. 10.1109/CVPR.2011.5995316 · DOI · Paper page
  23. 10.1109/CVPR.2015.7299009 · DOI
  24. devanne, 2014, 3D Human Action Recognition by Shape Analysis of Motion Trajectories on Riemannian Manifold, IEEE Transactions on Cybernetics, 99
  25. 10.1214/13-AOAS701 · doi:10.1214/13-aoas701
  26. 10.1109/CVPRW.2013.153 · DOI · Paper page
  27. gu, 2010, Action and Gait Recognition From Recovered 3-D Human Joints, IEEE Transactions on Systems Man and Cybernetics Part B, 40, 1021, 10.1109/TSMCB.2010.2043526 · DOI
  28. gowayyed, 2013, Histogram of Oriented Displacements (HOD): Describing Trajectories of Human Joints for Action Recognition, IJCAI
  29. 10.1109/CVPRW.2012.6239175 · DOI · Paper page
  30. 10.1080/00207720802184717 · doi:10.1080/00207720802184717
  31. 10.1109/CVPR.2015.7298934 · doi:10.1109/cvpr.2015.7298934
  32. reyes, 2011, Feature Weighting in Dynamic Time Warping for Gesture Recognition in Depth Data, ICCV Workshops
  33. 10.1109/CVPRW.2013.77 · DOI · Paper page
  34. said, 2007, Exact Principal Geodesic Analysis for Data on SO(3), EU-SIP CO
  35. sharpe, 1996, Differential Geometry
  36. shao, 2013, A New Descriptor for Multiple 3D Motion Trajectories Recognition, ICRA
  37. shen, 2006, Smooth Interpolation of Orientation by Rolling and Wrapping for Robot Motion Planning, ICRA
  38. 10.1109/ICCV.2005.90 · DOI · Paper page

Cited by

See all 213

Metadata

Authors
Vemulapalli, R., & Chellappa, R.
Venue
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2016-06
Pages
4471-4479
ISSN
1063-6919 (ISSN-L)
OpenAlex
W2442651457
Cited by
213
References
0
FWCI
8.22
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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Rolling Rotations for Recognizing Human Actions from 3D Skeletal Data. https://app.cochat.ai/papers/10.1109/cvpr.2016.484
The paper
Vemulapalli, R., & Chellappa, R. (2016). Rolling Rotations for Recognizing Human Actions from 3D Skeletal Data. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr.2016.484

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.