Bidirectional invariant representation of rigid body motions and its application to gesture recognition and reproduction
Open accessThe DOI matches its Crossref record; 46 of the 50 references it cites were found in a registry or an index.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Unlike SE(3), these invariants represent motion by breaking it down into magnitude and directional changes, unaffected by embodiment-specific factors such as viewpoints, reference frames, pose offsets, or scales.”
From LEGATO: Cross-Embodiment Imitation Using a Grasping Tool (2025) · cites this paper as [42]
In the citing paper
“In the DHB transformation, the motion of a rigid body is separated into position and orientation components using two frames.”
From LEGATO: Cross-Embodiment Imitation Using a Grasping Tool (2025) · cites this paper as [42]
In the citing paper
“The motion-invariant transform ϕ(•), used to compute L invar in Equation 5, follows the DHB motion-invariant framework [42].”
From LEGATO: Cross-Embodiment Imitation Using a Grasping Tool (2025) · cites this paper as [42]
Citations
Cites
A tutorial on hidden Markov models and selected applications in speech recognition
Rabiner, L. R. (1989) · Proceedings of the IEEE · doi:10.1109/5.18626 · Cited by 22,743 · cited 3×
“HMMs are used for gesture recognition.”
MethodBook Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 22,066 · cited 4×
“In order to focus on motion representations, we adopt a widely-used classification algorithm, the k -Nearest Neigh-bour classifier (Bishop et al. 2006), instead of developing a customized classification algorithm.”
MethodInfluentialScale-space and edge detection using anisotropic diffusion
Perona, P., & Malik, J. (1990) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.56205 · Cited by 12,119
Dynamic Programming Algorithm Optimization for Spoken Word Recognition
Sakoe, H., & Chiba, S. (1978) · IEEE Transactions on Acoustics Speech and Signal Processing · doi:10.1109/tassp.1978.1163055 · Cited by 6,727 · cited 3×
“In particular multi dimensional DTW (MD-DTW) algorithm in Sanguansat (2012) was used to find the optimal non-linear match (see Fig.”
MethodA Mathematical Introduction to Robotic Manipulation
Murray, R. M., Li, Z., & Sastry, S. S. (2017) · CRC Press eBooks · doi:10.1201/9781315136370 · Cited by 6,694 · cited 10×
“Two invariants represent the translational velocity along the ISA and the rotational velocity about the ISA.”
MethodInfluentialJaderberg, M., Simonyan, K., Zisserman, A., & Kavukcuoglu, K. (2015) · arXiv · doi:10.48550/arxiv.1506.02025 · Cited by 5,137 · cited 1×
“Jaderberg et al [13] propose to learn warping transformations from input data and this extra learnable layer can be inserted into CNNs to improve the recognition performance.”
BackgroundPattern Recognition and Machine Learning
Neal, R. M. (2007) · Technometrics · doi:10.1198/tech.2007.s518 · Cited by 4,571
A Kinematic Notation for Lower-Pair Mechanisms Based on Matrices
Denavit, J., & Hartenberg, R. S. (1955) · Journal of Applied Mechanics · doi:10.1115/1.4011045 · Cited by 4,551
Robotics: modelling, planning and control
(2009) · Choice Reviews Online · doi:10.5860/choice.46-6226 · Cited by 2,479 · cited 2×
“First, the pose of the linear and angular frames in each instant t is computed as: where are the elementary rotations of an angle α about the y and x axis (Siciliano et al. 2009), and 0 T = [ 0 0 0 ] .”
MethodMaximum likelihood estimates of linear dynamic systems
RAUCH, H. E., TUNG, F., & STRIEBEL, C. T. (1965) · AIAA Journal · doi:10.2514/3.3166 · Cited by 1,943 · cited 4×
“A more sophisticated, off-line filtering technique as the linear Kalman smoother (Rauch et al. 1965) used in Vochten et al.”
MethodInfluentialMining actionlet ensemble for action recognition with depth cameras
Wang, J., Liu, Z., Wu, Y., & Yuan, J. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6247813 · Cited by 1,512
View invariant human action recognition using histograms of 3D joints
Xia, L., Chen, C.-C., & Aggarwal, J. K. (2012) · 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2012.6239233 · Cited by 1,452 · cited 3×
“Recognition performances of DHB and approaches in Li et al. (2010) and Xia et al. (2012) are compared in Sect.”
MethodAction recognition based on a bag of 3D points
Li, W., Zhang, Z., & Liu, Z. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops · doi:10.1109/cvprw.2010.5543273 · Cited by 1,428 · cited 4×
“Recognition performances of DHB and approaches in Li et al. (2010) and Xia et al. (2012) are compared in Sect.”
BackgroundMethodInfluentialRobot Programming by Demonstration
Billard, A., Calinon, S., Dillmann, R., & Schaal, S. (2008) · Springer Handbook of Robotics · doi:10.1007/978-3-540-30301-5_60 · Cited by 1,002
Contour tracking by stochastic propagation of conditional density
Isard, M., & Blake, A. (1996) · Lecture Notes in Computer Science · doi:10.1007/bfb0015549 · Cited by 869 · cited 1×
“The condensation algorithm (Isard and Blake 1996) is used to incrementally match trajectory models to the multi-variate input data.”
MethodLearning human activities and object affordances from RGB-D videos
Koppula, H. S., Gupta, R., & Saxena, A. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913478446 · Cited by 683 · cited 1×
“…recognizing human actions (Wu and Huang 2001), gesture-based human–robot interaction (Waldherr et al. 2000; Burger et al. 2011; Lee et al. 2009), learning human activities (Koppula et al. 2013), tasks learning by demonstration (Billard et al. 2008; Lee and Nakamura 2010; Saveriano et al. 2015).”
BackgroundVision-Based Gesture Recognition: A Review
Wu, Y., & Huang, T. S. (1999) · Lecture Notes in Computer Science · doi:10.1007/3-540-46616-9_10 · Cited by 528 · cited 2×
“Examples include recognizing human actions (Wu and Huang 2001), gesture-based human–robot interaction (Waldherr et al. 2000; Burger et al. 2011; Lee et al. 2009), learning human activities (Koppula et al. 2013), tasks learning by demonstration (Billard et al. 2008; Lee and Nakamura 2010; Saveriano…”
BackgroundNumerical Differentiation of Noisy, Nonsmooth Data
Chartrand, R. (2011) · ISRN Applied Mathematics · doi:10.5402/2011/164564 · Cited by 444 · cited 2×
“The numerical computation of high order derivatives is sensitive to the noise in the data and round-off errors (Chartrand 2011).”
BackgroundMethodView-Invariant Representation and Recognition of Actions
Rao, C., Yilmaz, A., & Shah, M. (2002) · International Journal of Computer Vision · doi:10.1023/a:1020350100748 · Cited by 433 · cited 1×
“In Rao et al. (2002, 2003) gestures are represented by the spatio-temporal curvature of the Cartesian trajectory, that is invariant to roto-translations.”
BackgroundDifferential Geometry: Curves - Surfaces - Manifolds
Kühnel, W. (2002) · Cited by 386
A Gesture Based Interface for Human-Robot Interaction
Waldherr, S., Romero, R., & Thrun, S. (2000) · Autonomous Robots · doi:10.1023/a:1008918401478 · Cited by 320 · cited 2×
“Examples include recognizing human actions (Wu and Huang 2001), gesture-based human–robot interaction (Waldherr et al. 2000; Burger et al. 2011; Lee et al. 2009), learning human activities (Koppula et al. 2013), tasks learning by demonstration (Billard et al. 2008; Lee and Nakamura 2010; Saveriano…”
BackgroundGeometric invariants and object recognition
Weiss, I. (1993) · International Journal of Computer Vision · doi:10.1007/bf01539536 · Cited by 248 · cited 2×
“Three dimensional invariants under affine transformations are proposed in Zisserman and May-bank (1994) and Weiss (1993).”
BackgroundMethodBlack, M. J., & Jepson, A. D. (1998) · Lecture Notes in Computer Science · doi:10.1007/bfb0055712 · Cited by 193 · cited 2×
“In [3] human motions are modeled as temporal trajectories of estimated parameters (state) over time.”
BackgroundWSEAS TRANSACTIONS ON MATHEMATICS
(2020) · WSEAS TRANSACTIONS ON MATHEMATICS · doi:10.37394/23206 · Cited by 185
Learning Invariant Feature Hierarchies
LeCun, Y. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33863-2_51 · Cited by 166 · cited 1×
“Inspired by the recognition process in the visual cortex, LeCun (2012) presents a hierarchical architecture to learn, from visual inputs, features invariant to affine transformations and illumination.”
MethodLearning 4D action feature models for arbitrary view action recognition
Yan, P., Khan, S. M., & Shah, M. A. (2008) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2008.4587737 · Cited by 151 · cited 1×
“The 4D Action Feature Model (4D-AFM) is proposed in Yan et al. (2008) to recognize full-body gestures observed from arbitrary views.”
BackgroundExploiting Cyclic Symmetry in Convolutional Neural Networks
Dieleman, S., Fauw, J. D., & Kavukcuoglu, K. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.02660 · Cited by 149 · cited 2×
“In [9] the standard CNN is extended with four extra layers (slice, pool, roll and stack) which realize local invariance to rotations.”
BackgroundConvNets-Based Action Recognition from Depth Maps through Virtual Cameras and Pseudocoloring
Wang, P., Li, W., Gao, Z., Tang, C., Zhang, J., & Ogunbona, P. (2015) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2733373.2806296 · Cited by 104 · cited 1×
“CNNs are effectively used in Wang et al. (2015) to recognize human actions from input depth maps.”
BackgroundTwo-handed gesture recognition and fusion with speech to command a robot
Burger, B., Ferrané, I., Lerasle, F., & Infantes, G. (2011) · Autonomous Robots · doi:10.1007/s10514-011-9263-y · Cited by 96 · cited 2×
“The numerical computation of high order derivatives is sensitive to the noise in the data and round-off errors (Chartrand 2011).”
BackgroundMethodRecognition of human gestures and behaviour based on motion trajectories
Ψαρρού, Α., Gong, S., & Walter, M. (2002) · Image and Vision Computing · doi:10.1016/s0262-8856(02)00007-0 · Cited by 62
Incremental kinesthetic teaching of end-effector and null-space motion primitives
Saveriano, M., An, S.-I., & Lee, D. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139694 · Cited by 53 · cited 2×
“…recognizing human actions (Wu and Huang 2001), gesture-based human–robot interaction (Waldherr et al. 2000; Burger et al. 2011; Lee et al. 2009), learning human activities (Koppula et al. 2013), tasks learning by demonstration (Billard et al. 2008; Lee and Nakamura 2010; Saveriano et al. 2015).”
BackgroundSelf-citationInvariant Description of Rigid Body Motion Trajectories
Schutter, J. D. (2009) · Journal of Mechanisms and Robotics · doi:10.1115/1.4000524 · Cited by 48 · cited 21×
“This section describes theoretical relationships and differences between DHB and two state-of-the-art bidirectional invariant representations: EFS (Vochten et al. 2015) and DS DS invariants (De Schutter 2010) (De Schutter 2010).”
BackgroundMethodInfluentialOnline human walking imitation in task and joint space based on quadratic programming
Hu, K., Ott, C., & Lee, D. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907357 · Cited by 45 · cited 1×
“Mapping human motions to a humanoid robot considering differences in kinematics, dynamics and balancing stability is beyond the scope of this work but can be found in Hu and Lee (2012) and Hu et al. (2014).”
Self-citationA Bayesian approach for task recognition and future human activity prediction
Magnanimo, V., Saveriano, M., Rossi, S., & Lee, D. (2014) · IEEE RO-MAN · doi:10.1109/roman.2014.6926339 · Cited by 35 · cited 1×
“This approach is used in Magnanimo et al. (2014) to recognize human tasks by fusing gesture and object recognition into a dynamic Bayesian network (Bishop et al. 2006).”
MethodSelf-citationMimesis Model from Partial Observations for a Humanoid Robot
Lee, D., & Nakamura, Y. (2009) · The International Journal of Robotics Research · doi:10.1177/0278364909342282 · Cited by 34 · cited 1×
“…recognizing human actions (Wu and Huang 2001), gesture-based human–robot interaction (Waldherr et al. 2000; Burger et al. 2011; Lee et al. 2009), learning human activities (Koppula et al. 2013), tasks learning by demonstration (Billard et al. 2008; Lee and Nakamura 2010; Saveriano et al. 2015).”
BackgroundSelf-citationOn Signature Invariants for Effective Motion Trajectory Recognition
Wu, S., & Li, Y. (2008) · The International Journal of Robotics Research · doi:10.1177/0278364908091678 · Cited by 34 · cited 4×
“In Wu and Li (2008), a method is proposed to calculate FS invariants without using high-order derivatives.”
BackgroundMethodInfluentialComparison of rigid body motion trajectory descriptors for motion representation and recognition
Vochten, M., Laet, T. D., & Schutter, J. D. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139612 · Cited by 32 · cited 8×
“8, the sensitivity of numerical derivatives makes diffi-cult to estimate reliably the invariant values in Vochten et al. (2015)andDeSchutter(2010)andgeneratesanon-negligible reconstruction error.”
BackgroundMethodInfluentialMultiple Multidimensional Sequence Alignment Using Generalized Dynamic Time Warping
Sanguansat, P. (2012) · Cited by 32
A case against epipolar geometry
Zisserman, A., & Maybank, S. J. (1994) · Lecture notes in computer science · doi:10.1007/3-540-58240-1_4 · Cited by 30
Mimetic communication with impedance control for physical human-robot interaction
Lee, D., Ott, C., & Nakamura, Y. (2009) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2009.5152857 · Cited by 19 · cited 1×
“Examples include recognizing human actions (Wu and Huang 2001), gesture-based human–robot interaction (Waldherr et al. 2000; Burger et al. 2011; Lee et al. 2009), learning human activities (Koppula et al. 2013), tasks learning by demonstration (Billard et al. 2008; Lee and Nakamura 2010; Saveriano…”
BackgroundSelf-citationRecognition of 6 DOF rigid body motion trajectories using a coordinate-free representation
Schutter, J. D., Lello, E. D., Schutter, J. F. M. D., Matthysen, R., Benoit, T., & Laet, T. D. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5980060 · Cited by 18 · cited 2×
“A more sophisticated, off-line filtering technique as the linear Kalman smoother (Rauch et al. 1965) used in Vochten et al. (2015) and De Schutter et al. (2011) could further improve the performance.”
MethodA bidirectional invariant representation of motion for gesture recognition and reproduction
Soloperto, R., Saveriano, M., & Lee, D. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7140062 · Cited by 14 · cited 1×
“1 This work is based on our preliminary results presented in [36].”
BackgroundSelf-citationInvariant representation for user independent motion recognition
Saveriano, M., & Lee, D. (2013) · IEEE RO-MAN · doi:10.1109/roman.2013.6628422 · Cited by 13 · cited 4×
“According to De Schutter (2010) and Table 2 Note that the representation in Saveriano and Lee (2013) uses a subset ( e 2 v and e 2 ω ) of EFS invariants.”
BackgroundMethodInfluentialSelf-citationMotion trajectory reproduction from generalized signature description
Wu, S., & Li, Y. (2009) · Pattern Recognition · doi:10.1016/j.patcog.2009.05.019 · Cited by 13 · cited 9×
“The original trajectory can be reconstructed from EFS invariants by applying the method in Wu and Li (2010) to both the FS frames.”
BackgroundMethodInfluentialSpace-time invariants and video motion extraction from arbitrary viewpoints
Mizoguchi, M., & Sato, J. (2003) · doi:10.1109/icpr.2002.1047399 · Cited by 8
Piao, Y., Hayakawa, K., & Sato, J. (2005) · International Conference on Image and Graphics · doi:10.1109/icig.2004.134 · Cited by 4
Research works printed but not linked: 3
- Hu, K., & Lee, D. (2012). Biped locomotion primitive learning, control and prediction from human data. In 10th International IFAC symposium on robot control (SYROCO).
- Rao, C., Shah, M., & Syeda-Mahmood, T. (2003). Action recognition based on view invariant spatio-temporal analysis. In ACM multimedia.
- Schreiber, G., Stemmer, A., & Bischoff, R. (2010). The fast research interface for the kuka lightweight robot. In ICRA workshop on innovative robot control architectures for demanding (Research) applications (pp. 15–21).
Cited by
Soft Wrist-Worn Multi-Functional Sensor Array for Real-Time Hand Gesture Recognition
Dong, W., Yang, L., Gravina, R., & Fortino, G. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3050175 · Cited by 55
“Hand gesture recognition technologies have progressed 114 rapidly with different intelligent algorithms, such as Sup-115 port Vector Machines (SVM), Convolutional Neural Networks 116 (CNN), and Artificial Neural Networks (ANN) [25], [26].”
MethodGeneralizing demonstrated motion trajectories using coordinate-free shape descriptors
Vochten, M., Laet, T. D., & Schutter, J. D. (2019) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2019.103291 · Cited by 28
Identification of Common Force-based Robot Skills from the Human and Robot Perspective
Eiband, T., & Lee, D. (2021) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids47582.2021.9555681 · Cited by 12
Self-citationVochten, M., Mousavi, A., Verduyn, A., Laet, T. D., Aertbeliën, E., & Schutter, J. D. (2023) · IEEE Transactions on Robotics · doi:10.1109/tro.2023.3309230 · Cited by 10
“Invariant trajectory descriptors for motion have, for the large majority, been applied in motion recognition [20], [26], [27].”
BackgroundMethodInfluentialLEGATO: Cross-Embodiment Imitation Using a Grasping Tool
Seo, M., Park, H. A., Yuan, S., Zhu, Y., & Sentis, L. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3535182 · Cited by 11
“The term L invar is calculated as the L2 loss in the motion-invariant space, specifically using the DHB invariant transformation [41], ϕ ( · ) (see Appendix for details).”
Method
Metadata
- Authors
- Lee, D., Soloperto, R., & Saveriano, M.
- Affiliations
- Technical University of Munich (DE)
- University of Bologna (IT)
- Corresponding author
- Lee, Dongheui
- Venue
- Autonomous Robots
- Published
- 2017-06-15
- Volume
- 42
- Issue
- 1
- Pages
- 125-145
- ISSN
- 0929-5593 (ISSN-L)
- 1573-7527
- OpenAlex
- W2625596139
- Cited by
- 11
- References
- 50
- Citations by year
- 2025: 2 · 2023: 2 · 2021: 2 · 2020: 2 · 2019: 1 · 2018: 2
- FWCI
- 0.86
- Type
- journal article
- Language
- en
- Open access
- green
- mediatum.ub.tum.de
- Licence
- Locations
- Autonomous Robots (publishedVersion)
- elib (German Aerospace Center) (submittedVersion)
- Iris (University of Trento) (submittedVersion)
- mediaTUM – the media and publications repository of the Technical University Munich (Technical University Munich) (submittedVersion, other-oa)
- Topics
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Human Motion and Animation
- Physical Sciences › Computer Science › Human-Computer Interaction › Hand Gesture Recognition Systems
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Keywords
- rigid body motion, gesture recognition, human-robot interaction, robot motion generation, NAO robot, pose invariance, scale invariance
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.