The DOI matches its Crossref record.
Rolling Rotations for Recognizing Human Actions from 3D Skeletal Data
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.
Integrity signals
Registry
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.
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
- yang, 2012, Eigen Joints-based Action Recognition Using Naive-Bayes-Nearest-Neighbor, CVPR Workshops
- 10.1109/CVPR.2012.6247813 · DOI · Paper page
- 10.1109/CVPR.2014.82 · DOI · Paper page
- 10.1111/j.1467-8659.2009.01375.x · doi:10.1111/j.1467-8659.2009.01375.x
- sung, 2012, Unstructured Human Activity Detection from RGBD Images, ICRA
- 10.1109/ICCV.1998.710709 · DOI
- 10.1109/CVPRW.2012.6239233 · DOI · Paper page
- 10.1109/ICCV.2013.389 · DOI
- 10.1109/ICCV.2013.334 · DOI
- hüper, 2002, Smoothing Interpolation Curves on Manifolds with Applications to Path Planning, Mediter-ranean Conference on Control and Automation
- 10.1007/s10883-007-9027-3 · doi:10.1007/s10883-007-9027-3
- hussein, 2013, Human Action Recognition Using a Temporal Hierarchy of Covariance Descriptors on 3D Joint Locations, IJCAI
- 10.1007/s10851-009-0161-2 · DOI · Paper page
- 10.1109/TCSVT.2011.2181452 · DOI
- lv, 2006, Recognition and Segmentation of 3D Human Action Using HMM and Multi-class Adaboost, ECCV
- 10.1109/ICPR.2014.340 · doi:10.1109/icpr.2014.340
- 10.1109/CVPRW.2012.6239231 · DOI
- 10.1109/CVPRW.2013.76 · DOI · Paper page
- 10.1109/CVPR.2013.98 · DOI · Paper page
- 10.1109/TPAMI.2010.184 · DOI · Paper page
- caseiro, 2013, Rolling Riemannian Manifolds to Solve the Multiclass Classification Problem, CVPR
- 10.1109/CVPR.2011.5995316 · DOI · Paper page
- 10.1109/CVPR.2015.7299009 · DOI
- devanne, 2014, 3D Human Action Recognition by Shape Analysis of Motion Trajectories on Riemannian Manifold, IEEE Transactions on Cybernetics, 99
- 10.1214/13-AOAS701 · doi:10.1214/13-aoas701
- 10.1109/CVPRW.2013.153 · DOI · Paper page
- 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
- gowayyed, 2013, Histogram of Oriented Displacements (HOD): Describing Trajectories of Human Joints for Action Recognition, IJCAI
- 10.1109/CVPRW.2012.6239175 · DOI · Paper page
- 10.1080/00207720802184717 · doi:10.1080/00207720802184717
- 10.1109/CVPR.2015.7298934 · doi:10.1109/cvpr.2015.7298934
- reyes, 2011, Feature Weighting in Dynamic Time Warping for Gesture Recognition in Depth Data, ICCV Workshops
- 10.1109/CVPRW.2013.77 · DOI · Paper page
- said, 2007, Exact Principal Geodesic Analysis for Data on SO(3), EU-SIP CO
- sharpe, 1996, Differential Geometry
- shao, 2013, A New Descriptor for Multiple 3D Motion Trajectories Recognition, ICRA
- shen, 2006, Smooth Interpolation of Orientation by Rolling and Wrapping for Robot Motion Planning, ICRA
- 10.1109/ICCV.2005.90 · DOI · Paper page
Cited by
On Human Motion Prediction Using Recurrent Neural Networks
Martinez, J., Black, M. J., & Romero, J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.497 · Cited by 984
An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition
Si, C., Chen, W., Wang, W., Wang, L., & Tan, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00132 · Cited by 917
Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates
Liu, J., Shahroudy, A., Xu, D., Kot, A. C., & Wang, G. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2771306 · Cited by 530
First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations
Garcia-Hernando, G., Yuan, S., Baek, S., & Kim, T.-K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00050 · Cited by 519
Vision-based human activity recognition: a survey
Beddiar, D. R., Nini, B., Sabokrou, M., & Hadid, A. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09004-3 · Cited by 505
Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks
Wang, P., Li, Z., Hou, Y., & Li, W. (2016) · Proceedings of the 24th ACM international conference on Multimedia · doi:10.1145/2964284.2967191 · Cited by 383
Skeleton Optical Spectra-Based Action Recognition Using Convolutional Neural Networks
Hou, Y., Li, Z., Wang, P., & Li, W. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2628339 · Cited by 339
Deep Learning on Lie Groups for Skeleton-Based Action Recognition
Huang, Z., Wan, C., Probst, T., & Van Gool, L. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.137 · Cited by 276
3D Human Action Representation Learning via Cross-View Consistency Pursuit
Li, L., Wang, M., Ni, B., Wang, H., Yang, J., & Zhang, W. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00471 · Cited by 236
“To tackle skeletonbased action recognition tasks, early approaches are generally based on hand-craft features [33, 52, 49, 50].”
MS2L: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognition
Lin, L., Song, S., Yang, W., & Liu, J. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413548 · Cited by 223
Guo, T., Liu, H., Chen, Z., Liu, M., Wang, T., & Ding, R. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i1.19957 · Cited by 202
“Early skeleton-based action recognition methods are usually based on hand-crafted features (Wang et al. 2012; Vemulapalli, Ar-rate, and Chellappa 2014; Vemulapalli and Chellapa 2016).”
MethodMulti-Modality Multi-Task Recurrent Neural Network for Online Action Detection
Liu, J., Li, Y., Song, S., Xing, J., Lan, C., & Zeng, W. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2799968 · Cited by 62
SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-Supervised Skeleton Action Recognition
Wu, W., Hua, Y., Zheng, C., Wu, S., Chen, C., & Lu, A. (2023) · 2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) · doi:10.1109/icmew59549.2023.00045 · Cited by 60
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
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.