17.1.3.7.17 Human Action Recognition, Skeletal Representations

Chapter Contents (Back)
Action Recognition. Action Detection. Skeletal Action Recognition. Human Actions.
See also Human Action Recognition, Neural Nets for Skeletal Representations. Relate to:
See also Human Action Recognition and Detection Using Human Pose. And:
See also Human Action Recognition, Part Models, Human Pose.
See also Articulatd Action Recognition.

Shan, Y.H.[Yan-Hu], Zhang, Z.[Zhang], Yang, P.P.[Pei-Pei], Huang, K.Q.[Kai-Qi],
Adaptive Slice Representation for Human Action Classification,
CirSysVideo(25), No. 10, October 2015, pp. 1624-1636.
IEEE DOI 1511
BibRef
Earlier: A1, A2, A4, Only:
Learning Skeleton Stream Patterns with Slow Feature Analysis for Action Recognition,
Re-Id14(111-121).
Springer DOI 1504
feature extraction
See also Slow Feature Analysis for Human Action Recognition. BibRef

Shan, Y.H.[Yan-Hu], Zhang, Z.[Zhang], Zhang, J.G.[Jun-Ge], Huang, K.Q.[Kai-Qi], Wu, N.[Na], Hyun, O.S.[Oh Se],
Interest Point Selection with Spatio-temporal Context for Realistic Action Recognition,
AVSS12(94-99).
IEEE DOI 1211
BibRef

Zhou, Z.L.[Zhuo-Li], Song, M.L.[Ming-Li], Zhang, L.M.[Lu-Ming], Tao, D.C.[Da-Cheng], Bu, J.J.[Jia-Jun], Chen, C.[Chun],
kPose: A New Representation For Action Recognition,
ACCV10(III: 436-447).
Springer DOI 1011
BibRef

Shao, L.[Ling], Ji, L.[Ling], Liu, Y.[Yan], Zhang, J.G.[Jian-Guo],
Human action segmentation and recognition via motion and shape analysis,
PRL(33), No. 4, March 2012, pp. 438-445.
Elsevier DOI 1201
Human action segmentation; Motion analysis; PCOG; Motion history image; Human action recognition BibRef

Wu, D.[Di], Shao, L.[Ling],
Silhouette Analysis-Based Action Recognition Via Exploiting Human Poses,
CirSysVideo(23), No. 2, February 2013, pp. 236-243.
IEEE DOI 1301
BibRef
And:
Leveraging Hierarchical Parametric Networks for Skeletal Joints Based Action Segmentation and Recognition,
CVPR14(724-731)
IEEE DOI 1409

See also Deep Dynamic Neural Networks for Gesture Segmentation and Recognition. BibRef

Chaaraoui, A.A.[Alexandros Andre], Climent-Pérez, P.[Pau], Flórez-Revuelta, F.[Francisco],
Silhouette-based human action recognition using sequences of key poses,
PRL(34), No. 15, 2013, pp. 1799-1807.
Elsevier DOI 1309
Human action recognition BibRef

Chaaraoui, A.A.[Alexandros Andre], Padilla-Lopez, J.R., Flórez-Revuelta, F.[Francisco],
Fusion of Skeletal and Silhouette-Based Features for Human Action Recognition with RGB-D Devices,
CDC4CV13(91-97)
IEEE DOI 1403
feature extraction BibRef

Anwer, R.M.[Rao Muhammad], Khan, F.S.[Fahad Shahbaz], van de Weijer, J.[Joost], Laaksonen, J.T.[Jorma T.],
Top-Down Deep Appearance Attention for Action Recognition,
SCIA17(I: 297-309).
Springer DOI 1706
BibRef

Khan, F.S.[Fahad Shahbaz], Anwer, R.M.[Rao Muhammad], van de Weijer, J.[Joost], Felsberg, M.[Michael], Laaksonen, J.T.[Jorma T.],
Deep Semantic Pyramids for Human Attributes and Action Recognition,
SCIA15(341-353).
Springer DOI 1506
BibRef

Khan, F.S.[Fahad Shahbaz], van de Weijer, J.[Joost], Anwer, R.M.[Rao Muhammad], Felsberg, M.[Michael], Gatta, C.,
Semantic Pyramids for Gender and Action Recognition,
IP(23), No. 8, August 2014, pp. 3633-3645.
IEEE DOI 1408
BibRef

Khan, F.S.[Fahad Shahbaz], van de Weijer, J.[Joost], Anwer, R.M.[Rao Muhammad], Bagdanov, A.D.[Andrew D.], Felsberg, M.[Michael], Laaksonen, J.T.[Jorma T.],
Scale coding bag of deep features for human attribute and action recognition,
MVA(29), No. 1, January 2018, pp. 55-71.
Springer DOI 1801
BibRef
Earlier: A1, A2, A4, A5, Only:
Scale Coding Bag-of-Words for Action Recognition,
ICPR14(1514-1519)
IEEE DOI 1412
Encoding BibRef

Khan, F.S.[Fahad Shahbaz], Xu, J.L.[Jiao-Long], van de Weijer, J.[Joost], Bagdanov, A.D.[Andrew D.], Anwer, R.M., Lopez, A.M.,
Recognizing Actions Through Action-Specific Person Detection,
IP(24), No. 11, November 2015, pp. 4422-4432.
IEEE DOI 1509
BibRef

Ofli, F.[Ferda], Chaudhry, R.[Rizwan], Kurillo, G.[Gregorij], Vidal, R.[René], Bajcsy, R.[Ruzena],
Sequence of the most informative joints (SMIJ): A new representation for human skeletal action recognition,
JVCIR(25), No. 1, 2014, pp. 24-38.
Elsevier DOI 1502
BibRef
Earlier: HAU3D12(8-13).
IEEE DOI 1207
Human action representation BibRef

Pazhoumand-Dar, H.[Hossein], Lam, C.P.[Chiou-Peng], Masek, M.[Martin],
Joint movement similarities for robust 3D action recognition using skeletal data,
JVCIR(30), No. 1, 2015, pp. 10-21.
Elsevier DOI 1507
Human action recognition BibRef

Amor, B.B., Su, J., Srivastava, A.,
Action Recognition Using Rate-Invariant Analysis of Skeletal Shape Trajectories,
PAMI(38), No. 1, January 2016, pp. 1-13.
IEEE DOI 1601
Hidden Markov models BibRef

Cai, X., Zhou, W., Wu, L., Luo, J., Li, H.,
Effective Active Skeleton Representation for Low Latency Human Action Recognition,
MultMed(18), No. 2, February 2016, pp. 141-154.
IEEE DOI 1601
Acceleration BibRef

Azis, N.A., Jeong, Y.S., Choi, H.J., Iraqi, Y.,
Weighted averaging fusion for multi-view skeletal data and its application in action recognition,
IET-CV(10), No. 2, 2016, pp. 134-142.
DOI Link 1603
feature extraction BibRef

Jung, H.J.[Hyun-Joo], Hong, K.S.[Ki-Sang],
Modeling temporal structure of complex actions using Bag-of-Sequencelets,
PRL(85), No. 1, 2017, pp. 21-28.
Elsevier DOI 1612
BibRef
Earlier:
Enhanced Sequence Matching for Action Recognition from 3D Skeletal Data,
ACCV14(V: 226-240).
Springer DOI 1504
Action recognition BibRef

Jung, H.J.[Hyun-Joo], Hong, K.S.[Ki-Sang],
Versatile Model for Activity Recognition: Sequencelet Corpus Model,
FG18(325-332)
IEEE DOI 1806
Activity recognition, Indexes, Semantics, Support vector machines, Task analysis, Training, Training data, activity recognition, sequencelet BibRef

Qiao, R.Z.[Rui-Zhi], Liu, L.Q.[Ling-Qiao], Shen, C.H.[Chun-Hua], van den Hengel, A.J.[Anton J.],
Learning discriminative trajectorylet detector sets for accurate skeleton-based action recognition,
PR(66), No. 1, 2017, pp. 202-212.
Elsevier DOI 1704
Action recognition BibRef

Liu, M.Y.[Meng-Yuan], Liu, H.[Hong], Chen, C.[Chen],
Enhanced skeleton visualization for view invariant human action recognition,
PR(68), No. 1, 2017, pp. 346-362.
Elsevier DOI 1704
Human action recognition BibRef

Rahmani, H., Mian, A., Shah, M.,
Learning a Deep Model for Human Action Recognition from Novel Viewpoints,
PAMI(40), No. 3, March 2018, pp. 667-681.
IEEE DOI 1802
Knowledge transfer, Solid modeling, Training, Trajectory, Videos, Cross-view, view knowledge transfer BibRef

Rahmani, H., Bennamoun, M.,
Learning Action Recognition Model from Depth and Skeleton Videos,
ICCV17(5833-5842)
IEEE DOI 1802
human computer interaction, image motion analysis, image representation, image sensors, Videos BibRef

Cao, C.Q.[Cong-Qi], Zhang, Y.F.[Yi-Fan], Zhang, C., Lu, H.Q.[Han-Qing],
Body Joint Guided 3-D Deep Convolutional Descriptors for Action Recognition,
Cyber(48), No. 3, March 2018, pp. 1095-1108.
IEEE DOI 1802
Convolution, Estimation, Feature extraction, Kernel, Optical imaging, Skeleton, Trajectory, Action recognition, body joints, two-stream bilinear model BibRef

Li, R.[Rui], Liu, Z.Y.[Zhen-Yu], Tan, J.R.[Jian-Rong],
Human motion segmentation using collaborative representations of 3D skeletal sequences,
IET-CV(12), No. 4, June 2018, pp. 434-442.
DOI Link 1805
BibRef

Wang, H.S.[Hong-Song], Wang, L.[Liang],
Learning content and style: Joint action recognition and person identification from human skeletons,
PR(81), 2018, pp. 23-35.
Elsevier DOI 1806
Content and style, Action recognition, Person identification from motions, Skeleton transformation, Multi-task RNN BibRef

Chang, J.Y.[Ju Yong], Heo, Y.S.[Yong Seok],
Data Augmented Dynamic Time Warping for Skeletal Action Classification,
IEICE(E101-D), No. 6, June 2018, pp. 1562-1571.
WWW Link. 1806
BibRef

Papadopoulos, G.T.[Georgios T.], Daras, P.[Petros],
Human Action Recognition Using 3D Reconstruction Data,
CirSysVideo(28), No. 8, August 2018, pp. 1807-1823.
IEEE DOI 1808
BibRef
Earlier:
Local descriptions for human action recognition from 3D reconstruction data,
ICIP14(2814-2818)
IEEE DOI 1502
Shape, Feature extraction, Robustness, Estimation, Histograms, Videos, 3D flow, 3D reconstruction, 3D shape, action recognition. BibRef

Papadopoulos, G.T.[Georgios T.], Axenopoulos, A.[Apostolos], Daras, P.[Petros],
Real-Time Skeleton-Tracking-Based Human Action Recognition Using Kinect Data,
MMMod14(I: 473-483).
Springer DOI 1405
BibRef

Zhang, Y.[Yong], Shen, B.W.[Bo-Wei], Wang, S.F.[Shao-Fan], Kong, D.[Dehui], Yin, B.C.[Bao-Cai],
L0-regularization-based skeleton optimization from consecutive point sets of kinetic human body,
PandRS(143), 2018, pp. 124-133.
Elsevier DOI 1808
minimization, Skeleton optimization, Consecutive point sets, Kinetic human body BibRef

Boulahia, S.Y.[Said Yacine], Anquetil, E.[Eric], Multon, F.[Franck], Kulpa, R.[Richard],
CuDi3D: Curvilinear displacement based approach for online 3D action detection,
CVIU(174), 2018, pp. 57-69.
Elsevier DOI 1812
BibRef
Earlier: A1, A2, A4, A3:
HIF3D: Handwriting-Inspired Features for 3D skeleton-based action recognition,
ICPR16(985-990)
IEEE DOI 1705
Online action recognition, Skeleton-based approach, Human action detection, Curvilinear displacement, Skeleton data stream. Feature extraction, Handwriting recognition, HIF3D, Handwriting-Inspired Features, Human action recognition, Joint trajectory modelling, RGB-D data, Skeleton-based, features BibRef

Min, W.D.[Wei-Dong], Yao, L.Y.[Lei-Yue], Lin, Z.R.[Zhen-Rong], Liu, L.[Li],
Support vector machine approach to fall recognition based on simplified expression of human skeleton action and fast detection of start key frame using torso angle,
IET-CV(12), No. 8, December 2018, pp. 1133-1140.
DOI Link 1812
BibRef

Ghorbel, E.[Enjie], Boonaert, J.[Jacques], Boutteau, R.[Rémi], Lecoeuche, S.[Stéphane], Savatier, X.[Xavier],
An extension of kernel learning methods using a modified Log-Euclidean distance for fast and accurate skeleton-based Human Action Recognition,
CVIU(175), 2018, pp. 32-43.
Elsevier DOI 1812
Kernel methods, Symmetric positive semi-definite matrices, Human action recognition, SVM, Covariance matrices, Log-Euclidean distance BibRef

Fan, Z.X.[Zhao-Xuan], Zhao, X.[Xu], Lin, T.W.[Tian-Wei], Su, H.S.[Hai-Sheng],
Attention-Based Multiview Re-Observation Fusion Network for Skeletal Action Recognition,
MultMed(21), No. 2, February 2019, pp. 363-374.
IEEE DOI 1902
Skeleton, Nonhomogeneous media, Fuses, Task analysis, Visualization, Pose estimation, long short-term memory (LSTM) BibRef

Su, H.S.[Hai-Sheng], Zhao, X.[Xu], Lin, T.W.[Tian-Wei],
Cascaded Pyramid Mining Network for Weakly Supervised Temporal Action Localization,
ACCV18(II:558-574).
Springer DOI 1906
BibRef

Liu, S.M.[Shu-Ming], Zhao, X.[Xu], Su, H.S.[Hai-Sheng], Hu, Z.L.[Zhi-Lan],
TSI: Temporal Scale Invariant Network for Action Proposal Generation,
ACCV20(V:530-546).
Springer DOI 2103
BibRef

Lin, T.W.[Tian-Wei], Zhao, X.[Xu], Su, H.S.[Hai-Sheng], Wang, C.J.[Chong-Jing], Yang, M.[Ming],
BSN: Boundary Sensitive Network for Temporal Action Proposal Generation,
ECCV18(II: 3-21).
Springer DOI 1810
BibRef

Lin, T.W.[Tian-Wei], Zhao, X.[Xu], Su, H.S.[Hai-Sheng],
Joint Learning of Local and Global Context for Temporal Action Proposal Generation,
CirSysVideo(30), No. 12, December 2020, pp. 4899-4912.
IEEE DOI 2012
Proposals, Videos, Task analysis, Reliability, Convolution, Object detection, Robots, Temporal action proposal generation, untrimmed video BibRef

Qing, Z.W.[Zhi-Wu], Su, H.S.[Hai-Sheng], Gan, W.H.[Wei-Hao], Wang, D.L.[Dong-Liang], Wu, W.[Wei], Wang, X.[Xiang], Qiao, Y.[Yu], Yan, J.J.[Jun-Jie], Gao, C.X.[Chang-Xin], Sang, N.[Nong],
Temporal Context Aggregation Network for Temporal Action Proposal Refinement,
CVPR21(485-494)
IEEE DOI 2111
Location awareness, Benchmark testing, Reliability engineering, Proposals, Task analysis BibRef

Weng, J., Weng, C., Yuan, J., Liu, Z.,
Discriminative Spatio-Temporal Pattern Discovery for 3D Action Recognition,
CirSysVideo(29), No. 4, April 2019, pp. 1077-1089.
IEEE DOI 1904
Mutual information, Solid modeling, Skeleton, Target recognition, discriminative skeleton-based action recognition BibRef

Cavazza, J.[Jacopo], Morerio, P.[Pietro], Murino, V.[Vittorio],
Scalable and compact 3D action recognition with approximated RBF kernel machines,
PR(93), 2019, pp. 25-35.
Elsevier DOI 1906
Kernel machines, Kernel approximation, Action recognition, Skeletal joints, Covariance representation BibRef

Men, Q.H.[Qian-Hui], Leung, H.[Howard],
Retrieval of spatial-temporal motion topics from 3D skeleton data,
VC(35), No. 6-8, June 2018, pp. 973-984.
WWW Link. 1906
BibRef

Nie, Q., Wang, J., Wang, X., Liu, Y.,
View-Invariant Human Action Recognition Based on a 3D Bio-Constrained Skeleton Model,
IP(28), No. 8, August 2019, pp. 3959-3972.
IEEE DOI 1907
bone, feature extraction, gesture recognition, image motion analysis, image recognition, image representation, bio-constrained skeleton model BibRef

Li, Q.M.[Qi-Ming], Lin, W.X.[Wen-Xiong], Li, J.[Jun],
Human activity recognition using dynamic representation and matching of skeleton feature sequences from RGB-D images,
SP:IC(68), 2018, pp. 265-272.
Elsevier DOI 1810
Human activity recognition, Dynamic representation and matching, Shape dynamic time warping BibRef

Yang, Z.Y.[Zheng-Yuan], Li, Y.C.[Yun-Cheng], Yang, J.C.[Jian-Chao], Luo, J.B.[Jie-Bo],
Action Recognition With Spatio-Temporal Visual Attention on Skeleton Image Sequences,
CirSysVideo(29), No. 8, August 2019, pp. 2405-2415.
IEEE DOI 1908
BibRef
Earlier:
Action Recognition with Visual Attention on Skeleton Images,
ICPR18(3309-3314)
IEEE DOI 1812
Skeleton, Visualization, Optical imaging, Image recognition, Image sequences, visual attention. Semantics BibRef

Wei, P., Sun, H., Zheng, N.,
Learning Composite Latent Structures for 3D Human Action Representation and Recognition,
MultMed(21), No. 9, September 2019, pp. 2195-2208.
IEEE DOI 1909
Skeleton, Semantics, Hidden Markov models, Deep learning, Sun, Solid modeling, composite latent structure BibRef

Ghazal, S.[Sumaira], Khan, U.S.[Umar S.], Saleem, M.M.[Muhammad Mubasher], Rashid, N.[Nasir], Iqbal, J.[Javaid],
Human activity recognition using 2D skeleton data and supervised machine learning,
IET-IPR(13), No. 13, November 2019, pp. 2572-2578.
DOI Link 1911
BibRef

Liu, J.H.[Jia-Heng], Xu, D.[Dong],
GeometryMotion-Net: A Strong Two-Stream Baseline for 3D Action Recognition,
CirSysVideo(31), No. 12, December 2021, pp. 4711-4721.
IEEE DOI 2112
Feature extraction, Geometry, Cloud computing, Skeleton, Data mining, Deep learning, Point cloud, two-stream BibRef

Franco, A.[Annalisa], Magnani, A.[Antonio], Maio, D.[Dario],
A multimodal approach for human activity recognition based on skeleton and RGB data,
PRL(131), 2020, pp. 293-299.
Elsevier DOI 2004
Human activity recognition, Kinect sensor, Temporal images BibRef

Brighi, M.[Marco], Franco, A.[Annalisa], Maio, D.[Dario],
ActivityExplorer: A semi-supervised approach to discover unknown activity classes in HAR systems,
PRL(151), 2021, pp. 340-347.
Elsevier DOI 2110
Human Activity Recognition, Semi-supervised learning, Metric Learning BibRef

Franco, A.[Annalisa], Magnani, A.[Antonio], Maio, D.[Dario],
Joint Orientations from Skeleton Data for Human Activity Recognition,
CIAP17(I:152-162).
Springer DOI 1711
BibRef

Li, G.[Gang], Li, C.Y.[Chun-Yu],
Learning skeleton information for human action analysis using Kinect,
SP:IC(84), 2020, pp. 115814.
Elsevier DOI 2004
Human action recognition, Kinect sensor, Depth image, Human skeleton information BibRef

Li, Y.S.[Yan-Shan], Xia, R.J.[Rong-Jie], Liu, X.[Xing],
Learning shape and motion representations for view invariant skeleton-based action recognition,
PR(103), 2020, pp. 107293.
Elsevier DOI 2005
Human action recognition, Skeleton sequence, Representation learning, View invariant, Geometric Algebra BibRef

Ghorbel, E., Demisse, G., Aouada, D., Ottersten, B.,
Fast Adaptive Reparametrization (FAR) With Application to Human Action Recognition,
SPLetters(27), 2020, pp. 580-584.
IEEE DOI 2005
Manifolds, Skeleton, Algebra, Optimization, Benchmark testing, Shape, Feature extraction, Reparametrization, action recognition Riemannian manifolds BibRef

Li, J.A.[Jian-An], Xie, X.M.[Xue-Mei], Pan, Q.Z.[Qing-Zhe], Cao, Y.H.[Yu-Han], Zhao, Z.F.[Zhi-Fu], Shi, G.M.[Guang-Ming],
SGM-Net: Skeleton-guided multimodal network for action recognition,
PR(104), 2020, pp. 107356.
Elsevier DOI 2005
Action recognition, multi-modality, skeleton-guided BibRef

Kawamura, K.[Kazuki], Matsubara, T.[Takashi], Uehara, K.[Kuniaki],
Deep State-Space Model for Noise Tolerant Skeleton-Based Action Recognition,
IEICE(E103-D), No. 6, June 2020, pp. 1217-1225.
WWW Link. 2006
BibRef

Jiang, X., Xu, K., Sun, T.,
Action Recognition Scheme Based on Skeleton Representation With DS-LSTM Network,
CirSysVideo(30), No. 7, July 2020, pp. 2129-2140.
IEEE DOI 2007
Skeleton, Hidden Markov models, Noise reduction, Geometry, Robustness, Electrical engineering, STAE BibRef

Guo, H.J.[Hong-Ji], Ren, Z.[Zhou], Wu, Y.[Yi], Hua, G.[Gang], Ji, Q.[Qiang],
Uncertainty-Based Spatial-Temporal Attention for Online Action Detection,
ECCV22(IV:69-86).
Springer DOI 2211
BibRef

Cui, R.[Ran], Zhu, A.[Aichun], Wu, J.R.[Jing-Ran], Hua, G.[Gang],
Skeleton-based attention-aware spatial-temporal model for action detection and recognition,
IET-CV(14), No. 5, August 2020, pp. 177-184.
DOI Link 2007
BibRef

Cui, R.[Ran], Hua, G.[Gang], Wu, J.R.[Jing-Ran],
AP-GAN: Predicting skeletal activity to improve early activity recognition,
JVCIR(73), 2020, pp. 102923.
Elsevier DOI 2012
Early activity recognition, Activity prediction, Skeleton, GAN BibRef

Liu, X.[Xing], Li, Y.S.[Yan-Shan], Xia, R.J.[Rong-Jie],
Rotation-based spatial-temporal feature learning from skeleton sequences for action recognition,
SIViP(14), No. 6, September 2020, pp. 1227-1234.
WWW Link. 2008
BibRef

Hu, G., Cui, B., Yu, S.,
Joint Learning in the Spatio-Temporal and Frequency Domains for Skeleton-Based Action Recognition,
MultMed(22), No. 9, September 2020, pp. 2207-2220.
IEEE DOI 2008
Frequency-domain analysis, Transforms, Frequency synchronization, Semantics, Training, Skeleton, Data mining, Action recognition, multi-task learning BibRef

Zhang, T.[Tong], Zheng, W.M.[Wen-Ming], Cui, Z.[Zhen], Zong, Y.[Yuan], Li, C.L.[Chao-Long], Zhou, X.Y.[Xiao-Yan], Yang, J.[Jian],
Deep Manifold-to-Manifold Transforming Network for Skeleton-Based Action Recognition,
MultMed(22), No. 11, November 2020, pp. 2926-2937.
IEEE DOI 2010
Manifolds, Measurement, Covariance matrices, Feature extraction, Task analysis, Convolution, Kernel, Riemannian manifold, SPD matrix, action recognition BibRef

Lee, I., Kim, D., Lee, S.,
3-D Human Behavior Understanding Using Generalized TS-LSTM Networks,
MultMed(23), 2021, pp. 415-428.
IEEE DOI 2012
Skeleton, Hidden Markov models, Feature extraction, Dynamics, Machine learning, Solid modeling, Human action recognition, temporal sequence analysis BibRef

Shao, Z., Li, Y., Zhang, H.,
Learning Representations From Skeletal Self-Similarities for Cross-View Action Recognition,
CirSysVideo(31), No. 1, January 2021, pp. 160-174.
IEEE DOI 2101
Skeleton, Feature extraction, Learning systems, Wrapping, Spatiotemporal phenomena, view-invariant representation BibRef

Chen, L., Lu, J., Song, Z., Zhou, J.,
Recurrent Semantic Preserving Generation for Action Prediction,
CirSysVideo(31), No. 1, January 2021, pp. 231-245.
IEEE DOI 2101
Semantics, Machine learning, Skeleton, Predictive models, Feature extraction, skeleton based action BibRef

Bian, C., Feng, W., Wan, L., Wang, S.,
Structural Knowledge Distillation for Efficient Skeleton-Based Action Recognition,
IP(30), 2021, pp. 2963-2976.
IEEE DOI 2102
Skeleton, Training, Pose estimation, Feature extraction, Videos, Joints, Knowledge engineering, Skeleton-based action recognition, gradient revision BibRef

Yang, J., Liu, W., Yuan, J., Mei, T.,
Hierarchical Soft Quantization for Skeleton-Based Human Action Recognition,
MultMed(23), 2021, pp. 883-898.
IEEE DOI 2103
Skeleton, Feature extraction, Quantization (signal), Color, congenerous feature BibRef

Aouaidjia, K., Sheng, B., Li, P., Kim, J., Feng, D.D.,
Efficient Body Motion Quantification and Similarity Evaluation Using 3-D Joints Skeleton Coordinates,
SMCS(51), No. 5, May 2021, pp. 2774-2788.
IEEE DOI 2104
Skeleton, Measurement, Cameras, Sensors, Biological system modeling, Solid modeling, Pose estimation, Human-computer interaction, three-dimensional (3-D) human motion representation BibRef

Liu, X.L.[Xiao-Li], Yin, J.Q.[Jian-Qin], Liu, J.[Jin], Ding, P.X.[Peng-Xiang], Liu, J.[Jun], Liu, H.P.[Hua-Ping],
TrajectoryCNN: A New Spatio-Temporal Feature Learning Network for Human Motion Prediction,
CirSysVideo(31), No. 6, June 2021, pp. 2133-2146.
IEEE DOI 2106
Dynamics, Trajectory, Predictive models, Correlation, Biological system modeling, Robots, Benchmark testing, skeleton BibRef

Ding, P.X.[Peng-Xiang], Yin, J.Q.[Jian-Qin],
Towards More Realistic Human Motion Prediction With Attention to Motion Coordination,
CirSysVideo(32), No. 9, September 2022, pp. 5846-5858.
IEEE DOI 2209
Dynamics, Feature extraction, Predictive models, Adaptation models, Data mining, Skeleton, Convolution, Human motion prediction, enriched dynamics BibRef

Gupta, P.[Pranay], Thatipelli, A.[Anirudh], Aggarwal, A.[Aditya], Maheshwari, S.[Shubh], Trivedi, N.[Neel], Das, S.[Sourav], Sarvadevabhatla, R.K.[Ravi Kiran],
Quo Vadis, Skeleton Action Recognition?,
IJCV(129), No. 7, July 2021, pp. 2097-2112.
Springer DOI 2106
BibRef

Shen, X.P.[Xiang-Pei], Ding, Y.R.[Yan-Rui],
Human skeleton representation for 3D action recognition based on complex network coding and LSTM,
JVCIR(82), 2022, pp. 103386.
Elsevier DOI 2201
Skeleton-based action recognition, Complex network coding, LSTM, Feature extraction BibRef

Zang, Y.[Ying], Yang, D.S.[Dong-Sheng], Liu, T.J.[Tian-Jiao], Li, H.[Hui], Zhao, S.G.[Shu-Guang], Liu, Q.S.[Qing-Shan],
SparseShift-GCN: High precision skeleton-based action recognition,
PRL(153), 2022, pp. 136-143.
Elsevier DOI 2201
BibRef

Kong, J.[Jun], Bian, Y.H.[Yu-Hang], Jiang, M.[Min],
MTT: Multi-Scale Temporal Transformer for Skeleton-Based Action Recognition,
SPLetters(29), 2022, pp. 528-532.
IEEE DOI 2202
Feature extraction, Transformers, Kernel, Skeleton, Data mining, Task analysis, Convolution, Skeleton-based action recognition, multi-scale temporal embedding BibRef

Song, S.[Sijie], Liu, J.Y.[Jia-Ying], Lin, L.[Lilang], Guo, Z.M.[Zong-Ming],
Learning to Recognize Human Actions From Noisy Skeleton Data Via Noise Adaptation,
MultMed(24), 2022, pp. 1152-1163.
IEEE DOI 2203
Skeleton, Noise measurement, Adaptation models, Feature extraction, Cameras, Pose estimation, Action recognition, noisy skeletons, noise adaptation BibRef

Liu, M.Y.[Meng-Yuan], Bao, Y.[Youneng], Liang, Y.S.[Yong-Sheng], Meng, F.[Fanyang],
Spatial-Temporal Asynchronous Normalization for Unsupervised 3D Action Representation Learning,
SPLetters(29), 2022, pp. 632-636.
IEEE DOI 2203
Skeleton, Shape, Decoding, Task analysis, Representation learning, Data mining, 3D action, representation learning BibRef

Ng, W.[Wing], Zhang, M.Y.[Ming-Yang], Wang, T.[Ting],
Multi-Localized Sensitive Autoencoder-Attention-LSTM For Skeleton-based Action Recognition,
MultMed(24), 2022, pp. 1678-1690.
IEEE DOI 2204
Skeleton, Feature extraction, Joints, Hidden Markov models, Convolution, Task analysis, Bones, Localized Stochastic Sensitive Autoencoder (LiSSA) BibRef

Wang, H.R.[Hao-Ran], Yu, B.S.[Bao-Sheng], Li, J.Q.[Jia-Qi], Zhang, L.L.[Lin-Lin], Chen, D.Y.[Dong-Yue],
Multi-Stream Interaction Networks for Human Action Recognition,
CirSysVideo(32), No. 5, May 2022, pp. 3050-3060.
IEEE DOI 2205
Skeleton, Proposals, Footwear, Deep learning, Image recognition, Fuses, Adaptation models, Temporal HOI analysis, human action recognition BibRef

Xia, R.J.[Rong-Jie], Li, Y.S.[Yan-Shan], Luo, W.H.[Wen-Han],
LAGA-Net: Local-and-Global Attention Network for Skeleton Based Action Recognition,
MultMed(24), 2022, pp. 2648-2661.
IEEE DOI 2205
Skeleton, Feature extraction, Joints, Adaptation models, Kernel, Computational modeling, Motion Enhancement BibRef

Sun, B.[Bin], Wang, S.F.[Shao-Fan], Kong, D.[Dehui], Wang, L.C.[Li-Chun], Yin, B.C.[Bao-Cai],
Real-Time Human Action Recognition Using Locally Aggregated Kinematic-Guided Skeletonlet and Supervised Hashing-by-Analysis Model,
Cyber(52), No. 6, June 2022, pp. 4837-4849.
IEEE DOI 2207
Feature extraction, Real-time systems, Computational modeling, Joints, Solid modeling, Kinematics, Analytical models, sparse representation BibRef

Zhou, J.X.[Jia-Xin], Komuro, T.[Takashi],
An asymmetrical-structure auto-encoder for unsupervised representation learning of skeleton sequences,
CVIU(222), 2022, pp. 103491.
Elsevier DOI 2209
BibRef
And:
Recognizing Fall Actions from Videos Using Reconstruction Error of Variational Autoencoder,
ICIP19(3372-3376)
IEEE DOI 1910
Action recognition, Unsupervised representation learning. Image sequence analysis, Video surveillance BibRef

Rao, H.C.[Hao-Cong], Wang, S.Q.[Si-Qi], Hu, X.P.[Xi-Ping], Tan, M.K.[Ming-Kui], Guo, Y.[Yi], Cheng, J.[Jun], Liu, X.W.[Xin-Wang], Hu, B.[Bin],
A Self-Supervised Gait Encoding Approach With Locality-Awareness for 3D Skeleton Based Person Re-Identification,
PAMI(44), No. 10, October 2022, pp. 6649-6666.
IEEE DOI 2209
Skeleton, Encoding, Task analysis, Computational modeling, Solid modeling, Feature extraction, contrastive learning BibRef

Liu, C.W.[Cui-Wei], Zhao, X.X.[Xiao-Xue], Li, Z.K.[Zhao-Kui], Yan, Z.[Zhuo], Du, C.[Chong],
A Novel Two-Stage Knowledge Distillation Framework for Skeleton-Based Action Prediction,
SPLetters(29), 2022, pp. 1918-1922.
IEEE DOI 2209
Adaptation models, Predictive models, Skeleton, Training, Probability distribution, Writing, Action prediction, skeletons BibRef

Liu, K.Y.[Kai-Yuan], Li, Y.H.[Yun-Heng], Xu, Y.F.[Yuan-Feng], Liu, S.[Shuai], Liu, S.L.[Sheng-Lan],
Spatial Focus Attention for Fine-Grained Skeleton-Based Action Tasks,
SPLetters(29), 2022, pp. 1883-1887.
IEEE DOI 2209
Task analysis, Topology, Skeleton, Sports, Semantics, Heuristic algorithms, Encoding, temporal action segmentation BibRef

Kim, B.[Boeun], Choi, J.Y.[Jin Young],
Learning spectral transform for 3D human motion prediction,
CVIU(223), 2022, pp. 103548.
Elsevier DOI 2210
Human motion prediction, 3D Human motion prediction, Skeleton-based human motion prediction, Spectral transform BibRef

Nguyen, T.T.[Tien-Thanh], Pham, D.T.[Dinh-Tan], Vu, H.[Hai], Le, T.L.[Thi-Lan],
A robust and efficient method for skeleton-based human action recognition and its application for cross-dataset evaluation,
IET-CV(16), No. 8, 2022, pp. 709-726.
DOI Link 2210
BibRef

Farnoosh, A.[Amirreza], Ostadabbas, S.[Sarah],
Dynamical Deep Generative Latent Modeling of 3D Skeletal Motion,
IJCV(130), No. 11, November 2022, pp. 2695-2706.
Springer DOI 2210
BibRef

Ma, H.[Hao], Yang, Z.[Zaiyue], Liu, H.Y.[Hao-Yang],
Fine-Grained Unsupervised Temporal Action Segmentation and Distributed Representation for Skeleton-Based Human Motion Analysis,
Cyber(52), No. 12, December 2022, pp. 13411-13424.
IEEE DOI 2212
Motion segmentation, Hidden Markov models, Semantics, Analytical models, Motion analysis, Distributed representation, temporal action segmentation BibRef

Liu, Z.G.[Zhen-Guang], Wu, S.[Shuang], Jin, S.Y.[Shu-Yuan], Ji, S.[Shouling], Liu, Q.[Qi], Lu, S.J.[Shi-Jian], Cheng, L.[Li],
Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction,
PAMI(45), No. 1, January 2023, pp. 681-697.
IEEE DOI 2212
Context modeling, Mice, Joints, Predictive models, Kinematics, Task analysis, Motion prediction, motion context, pose representation BibRef

Song, Y.F.[Yi-Fan], Zhang, Z.[Zhang], Shan, C.F.[Cai-Feng], Wang, L.[Liang],
Constructing Stronger and Faster Baselines for Skeleton-Based Action Recognition,
PAMI(45), No. 2, February 2023, pp. 1474-1488.
IEEE DOI 2301
Computational modeling, Skeleton, Feature extraction, Convolution, Task analysis, Compounds, Training, Action recognition, separable convolution BibRef

Wen, Y.H.[Yu-Hui], Gao, L.[Lin], Fu, H.B.[Hong-Bo], Zhang, F.L.[Fang-Lue], Xia, S.H.[Shi-Hong], Liu, Y.J.[Yong-Jin],
Motif-GCNs With Local and Non-Local Temporal Blocks for Skeleton-Based Action Recognition,
PAMI(45), No. 2, February 2023, pp. 2009-2023.
IEEE DOI 2301
Skeleton, Feature extraction, Joints, Convolutional codes, Topology, Training, Sparse matrices, Action recognition, skeleton sequence BibRef

Cui, M.M.[Meng-Meng], Wang, W.[Wei], Zhang, K.[Kunbo], Sun, Z.A.[Zhen-An], Wang, L.[Liang],
Pose-Appearance Relational Modeling for Video Action Recognition,
IP(32), 2023, pp. 295-308.
IEEE DOI 2301
Visualization, Solid modeling, Skeleton, Feature extraction, Optical flow, Context modeling, Action recognition, temporal attention LSTM BibRef

Li, Z.H.[Zhi-Heng], Gong, X.Y.[Xu-Yuan], Song, R.[Ran], Duan, P.[Peng], Liu, J.[Jun], Zhang, W.[Wei],
SMAM: Self and Mutual Adaptive Matching for Skeleton-Based Few-Shot Action Recognition,
IP(32), 2023, pp. 392-402.
IEEE DOI 2301
Skeleton, Feature extraction, Training, Task analysis, Convolution, Topology, Semantics, Skeleton-based, action recognition, few-shot learning BibRef

Gao, X.H.[Xue-Hao], Yang, Y.[Yang], Zhang, Y.M.[Yi-Meng], Li, M.[Maosen], Yu, J.G.[Jin-Gang], Du, S.[Shaoyi],
Efficient Spatio-Temporal Contrastive Learning for Skeleton-Based 3-D Action Recognition,
MultMed(25), 2023, pp. 405-417.
IEEE DOI 2302
Task analysis, Skeleton, Encoding, Training, Feature extraction, Visualization, self-supervised method, observation scene, 3D action recognition BibRef

Khezerlou, F., Baradarani, A., Balafar, M.A.,
A convolutional autoencoder model with weighted multi-scale attention modules for 3D skeleton-based action recognition,
JVCIR(92), 2023, pp. 103781.
Elsevier DOI 2303
Human action recognition, Motion trajectories, 3DPo-CDP descriptor, Change direction patterns, Pose features, WMS block BibRef

Gedamu, K.[Kumie], Ji, Y.L.[Yan-Li], Gao, L.[LingLing], Yang, Y.[Yang], Shen, H.T.[Heng Tao],
Relation-mining self-attention network for skeleton-based human action recognition,
PR(139), 2023, pp. 109455.
Elsevier DOI 2304
Action recognition, Relation-mining self-attention, Pairwise self-attention, Unary self-attention, Position attention BibRef

Nikpour, B.[Bahareh], Armanfard, N.[Narges],
Spatio-temporal hard attention learning for skeleton-based activity recognition,
PR(139), 2023, pp. 109428.
Elsevier DOI 2304
Temporal attention, Spatial attention, Spatio-temporal attention, Activity recognition, Deep reinforcement learning BibRef

Wang, W.Q.[Wen-Qian], Chang, F.[Faliang], Liu, C.S.[Chun-Sheng], Li, G.X.[Guang-Xin], Wang, B.[Bin],
GA-Net: A Guidance Aware Network for Skeleton-Based Early Activity Recognition,
MultMed(25), 2023, pp. 1061-1073.
IEEE DOI 2305
Measurement, Skeleton, Dams, Feature extraction, Task analysis, Spatiotemporal phenomena, metric learning BibRef

Dai, M.[Meng], Sun, Z.H.[Zhong-Hua], Wang, T.Y.[Tian-Yi], Feng, J.C.[Jin-Chao], Jia, K.[Kebin],
Global spatio-temporal synergistic topology learning for skeleton-based action recognition,
PR(140), 2023, pp. 109540.
Elsevier DOI 2305
Action recognition, Spatio-temporal synergistic, Skeleton, Topology learning BibRef

Zhang, Y.[Yu], Sun, Z.H.[Zhong-Hua], Dai, M.[Meng], Feng, J.C.[Jin-Chao], Jia, K.[Kebin],
Cross-Scale Spatiotemporal Refinement Learning for Skeleton-Based Action Recognition,
SPLetters(31), 2024, pp. 441-445.
IEEE DOI 2402
Spatiotemporal phenomena, Semantics, Convolution, Feature extraction, Correlation, Solid modeling, Joints, cross-scale fusion BibRef

Xu, L.Y.[Lei-Yang], Wang, Q.[Qiang], Lin, X.T.[Xiao-Tian], Yuan, L.[Lin],
An efficient framework for few-shot skeleton-based temporal action segmentation,
CVIU(232), 2023, pp. 103707.
Elsevier DOI 2305
Temporal action segmentation, Data segmentation, Synthetic action sequences, Connectionist temporal classification BibRef

Liu, W.X.[Wen-Xuan], Zhong, X.[Xian], Zhou, Z.[Zhuo], Jiang, K.[Kui], Wang, Z.[Zheng], Lin, C.W.[Chia-Wen],
Dual-Recommendation Disentanglement Network for View Fuzz in Action Recognition,
IP(32), 2023, pp. 2719-2733.
IEEE DOI 2305
Feature extraction, Optical flow, Visualization, Computer science, Skeleton, Predictive models, Training, Action recognition, view fuzz, mutual learning BibRef

Peng, K.Y.[Kun-Yu], Roitberg, A.[Alina], Yang, K.L.[Kai-Lun], Zhang, J.M.[Jia-Ming], Stiefelhagen, R.[Rainer],
Delving Deep Into One-Shot Skeleton-Based Action Recognition With Diverse Occlusions,
MultMed(25), 2023, pp. 1489-1504.
IEEE DOI 2305
Transformers, Task analysis, Benchmark testing, Joints, Prototypes, Image recognition, human activity recognition, representation learning BibRef

Zeng, Q.Y.[Qin-Yang], Liu, C.J.[Cheng-Ju], Liu, M.[Ming], Chen, Q.J.[Qi-Jun],
Contrastive 3D Human Skeleton Action Representation Learning via CrossMoCo With Spatiotemporal Occlusion Mask Data Augmentation,
MultMed(25), 2023, pp. 1564-1574.
IEEE DOI 2305
Skeleton, Feature extraction, Spatiotemporal phenomena, Data mining, Joints, Learning systems, Cross contrastive learning, human skeleton action recognition BibRef

Li, D.[Ding], Tang, Y.Q.[Yong-Qiang], Zhang, Z.Z.[Zhi-Zhong], Zhang, W.S.[Wen-Sheng],
Cross-stream contrastive learning for self-supervised skeleton-based action recognition,
IVC(135), 2023, pp. 104689.
Elsevier DOI 2306
Self-supervised learning, Contrastive learning, Skeleton-based action recognition BibRef

Liu, H.W.[Hao-Wei], Liu, Y.C.[Yong-Cheng], Chen, Y.X.[Yu-Xin], Yuan, C.F.[Chun-Feng], Li, B.[Bing], Hu, W.M.[Wei-Ming],
TranSkeleton: Hierarchical Spatial-Temporal Transformer for Skeleton-Based Action Recognition,
CirSysVideo(33), No. 8, August 2023, pp. 4137-4148.
IEEE DOI 2308
Transformers, Skeleton, Computational modeling, Feature extraction, Convolution, Topology, Correlation, long-range temporal dependencies BibRef

Lv, J.R.[Jin-Rong], Gong, X.[Xun],
Multi-Grained Temporal Segmentation Attention Modeling for Skeleton-Based Action Recognition,
SPLetters(30), 2023, pp. 927-931.
IEEE DOI 2308
Skeleton, Feature extraction, Transformers, Topology, Computational modeling, Motion segmentation, Task analysis, transformer BibRef

Yang, S.Y.[Si-Yuan], Liu, J.[Jun], Lu, S.J.[Shi-Jian], Hwa, E.M.[Er Meng], Hu, Y.J.[Yong-Jian], Kot, A.C.[Alex C.],
Self-Supervised 3D Action Representation Learning With Skeleton Cloud Colorization,
PAMI(46), No. 1, January 2024, pp. 509-524.
IEEE DOI 2312
BibRef
Earlier: A1, A2, A3, A4, A6, Only:
Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning,
ICCV21(13403-13413)
IEEE DOI 2203
Representation learning, Point cloud compression, Image color analysis, Supervised learning, Stacking, BibRef

Pang, C.[Chen], Lu, X.Q.[Xue-Quan], Lyu, L.[Lei],
Skeleton-Based Action Recognition Through Contrasting Two-Stream Spatial-Temporal Networks,
MultMed(25), 2023, pp. 8699-8711.
IEEE DOI 2312
BibRef

Pan, Q.Z.[Qing-Zhe], Zhao, Z.[Zhifu], Xie, X.M.[Xue-Mei], Li, J.A.[Jian-An], Cao, Y.H.[Yu-Han], Shi, G.M.[Guang-Ming],
View-Normalized and Subject-Independent Skeleton Generation for Action Recognition,
CirSysVideo(33), No. 12, December 2023, pp. 7398-7412.
IEEE DOI 2312
BibRef

Xu, S.H.[Shi-Hao], Rao, H.C.[Hao-Cong], Hu, X.P.[Xi-Ping], Cheng, J.[Jun], Hu, B.[Bin],
Prototypical Contrast and Reverse Prediction: Unsupervised Skeleton Based Action Recognition,
MultMed(25), 2023, pp. 624-634.
IEEE DOI 2302
Skeleton, Prototypes, Encoding, Task analysis, Semantics, Decoding, Prediction algorithms, Prototypical contrast, skeleton based action recognition BibRef

Qin, H.[Hushan], Cheng, J.[Jun], Song, C.Q.[Cheng-Qun], Hao, F.[Fusheng], Cheng, Q.[Qin],
Structure-Preserving View-Invariant Skeleton Representation for Action Detection,
ICPR22(3190-3196)
IEEE DOI 2212
Representation learning, Limiting, Stacking, Discrete Fourier transforms, Feature extraction, Skeleton, skeleton representation BibRef

Guan, S.[Shannan], Yu, X.[Xin], Huang, W.[Wei], Fang, G.[Gengfa], Lu, H.Y.[Hai-Yan],
DMMG: Dual Min-Max Games for Self-Supervised Skeleton-Based Action Recognition,
IP(33), 2024, pp. 395-407.
IEEE DOI 2401
BibRef

Li, Y.H.[Yun-Heng], Liu, K.Y.[Kai-Yuan], Liu, S.L.[Sheng-Lan], Feng, L.[Lin], Qiao, H.[Hong],
Involving Distinguished Temporal Graph Convolutional Networks for Skeleton-Based Temporal Action Segmentation,
CirSysVideo(34), No. 1, January 2024, pp. 647-660.
IEEE DOI 2401
BibRef

Wu, C.[Cong], Wu, X.J.[Xiao-Jun], Xu, T.Y.[Tian-Yang], Shen, Z.[Zhongwei], Kittler, J.V.[Josef V.],
Motion Complement and Temporal Multifocusing for Skeleton-Based Action Recognition,
CirSysVideo(34), No. 1, January 2024, pp. 34-45.
IEEE DOI Code:
WWW Link. 2401
BibRef

He, X.T.[Xing-Tong], Liu, X.[Xu], Jiao, L.C.[Li-Cheng],
Global Shapes and Salient Joints Features Learning for Skeleton-Based Action Recognition,
SPLetters(31), 2024, pp. 206-210.
IEEE DOI 2401
BibRef

Qiu, H.[Helei], Hou, B.[Biao],
Multi-grained clip focus for skeleton-based action recognition,
PR(148), 2024, pp. 110188.
Elsevier DOI 2402
Action recognition, Skeleton, Multi-grain, Self-attention BibRef

Song, W.F.[Wen-Feng], Chu, T.[Tangli], Li, S.[Shuai], Li, N.N.[Nan-Nan], Hao, A.[Aimin], Qin, H.[Hong],
Joints-Centered Spatial-Temporal Features Fused Skeleton Convolution Network for Action Recognition,
MultMed(26), 2024, pp. 4602-4616.
IEEE DOI 2403
Skeleton, Feature extraction, Convolution, Visualization, Task analysis, Joints, Data mining, PDE diffusion BibRef

Guo, T.Y.[Tian-Yu], Liu, M.Y.[Meng-Yuan], Liu, H.[Hong], Wang, G.Q.[Guo-Quan], Li, W.H.[Wen-Hao],
Improving self-supervised action recognition from extremely augmented skeleton sequences,
PR(150), 2024, pp. 110333.
Elsevier DOI Code:
WWW Link. 2403
Self-supervised skeleton-based action recognition, Contrastive learning BibRef

Wang, G.Q.[Guo-Quan], Liu, M.Y.[Meng-Yuan], Liu, H.[Hong], Guo, P.[Peini], Wang, T.[Ti], Guo, J.W.[Jing-Wen], Fan, R.J.[Rui-Jia],
Augmented skeleton sequences with hypergraph network for self-supervised group activity recognition,
PR(152), 2024, pp. 110478.
Elsevier DOI Code:
WWW Link. 2405
Self-supervised learning, Skeleton-based group activity recognition, Hypergraph learning BibRef

Gu, C.Z.[Chun-Zhi], Zhang, C.[Chao], Kuriyama, S.[Shigeru],
Orientation-aware leg movement learning for action-driven human motion prediction,
PR(150), 2024, pp. 110317.
Elsevier DOI 2403
Stochastic human motion prediction, Motion transition learning, Deep generative model BibRef

Yin, X.P.[Xin-Peng], Zhong, J.Q.[Jian-Qi], Lian, D.L.[De-Liang], Cao, W.M.[Wen-Ming],
Spatiotemporal Progressive Inward-Outward Aggregation Network for skeleton-based action recognition,
PR(150), 2024, pp. 110262.
Elsevier DOI 2403
Action recognition, Graph convolutional networks, Progressive aggregation, Self-attention mechanism BibRef

Myung, W.[Woomin], Su, N.[Nan], Xue, J.H.[Jing-Hao], Wang, G.J.[Gui-Jin],
DeGCN: Deformable Graph Convolutional Networks for Skeleton-Based Action Recognition,
IP(33), 2024, pp. 2477-2490.
IEEE DOI 2404
Convolution, Adaptation models, Topology, Deformable models, Correlation, Convolutional neural networks, Laplace equations, deformable convolution BibRef

Shi, J.Y.[Jun-Yu], Zhong, J.Q.[Jian-Qi], Cao, W.M.[Wen-Ming],
Multi-Semantics Aggregation Network Based on the Dynamic-Attention Mechanism for 3D Human Motion Prediction,
MultMed(26), 2024, pp. 5194-5206.
IEEE DOI 2404
Semantics, Dynamics, Convolution, Predictive models, Feature extraction, Correlation, Frequency-domain analysis, skeleton-based data processing BibRef

Zhang, W.X.[Wen-Xian],
Scene context-aware graph convolutional network for skeleton-based action recognition,
IET-CV(18), No. 3, 2024, pp. 343-354.
DOI Link 2404
graph theory, image classification, image recognition BibRef

Li, C.K.[Chuan-Kun], Li, S.[Shuai], Gao, Y.B.[Yan-Bo], Zhou, L.J.[Li-Juan], Li, W.Q.[Wan-Qing],
Static graph convolution with learned temporal and channel-wise graph topology generation for skeleton-based action recognition,
CVIU(244), 2024, pp. 104012.
Elsevier DOI 2405
Action recognition, Skeleton data, Static graph topology, Graph convolutional networks BibRef

Diao, Y.F.[Yun-Feng], Wang, H.[He], Shao, T.[Tianjia], Yang, Y.L.[Yong-Liang], Zhou, K.[Kun], Hogg, D.[David], Wang, M.[Meng],
Understanding the vulnerability of skeleton-based Human Activity Recognition via black-box attack,
PR(153), 2024, pp. 110564.
Elsevier DOI 2405
Black-box attack, Skeletal action recognition, Adversarial robustness, On-manifold adversarial samples BibRef

Yang, S.Y.[Si-Yuan], Liu, J.[Jun], Lu, S.J.[Shi-Jian], Hwa, E.M.[Er Meng], Kot, A.C.[Alex C.],
One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching,
PAMI(46), No. 7, July 2024, pp. 5149-5156.
IEEE DOI 2406
Skeleton, Semantics, Task analysis, Optimal matching, Measurement, Convolutional neural networks, Adaptation models, skeleton action recognition BibRef

Nan, H.[Hai], Ye, Q.[Qilang], Yu, Z.T.[Zi-Tong], An, K.[Kang],
3sG: Three-stage guidance for indoor human action recognition,
IET-IPR(18), No. 8, 2024, pp. 2000-2010.
DOI Link 2406
Indoor is more fine-grained action. convolutional neural nets BibRef

Yang, D.[Di], Wang, Y.H.[Yao-Hui], Dantcheva, A.[Antitza], Garattoni, L.[Lorenzo], Francesca, G.[Gianpiero], Brémond, F.[François],
View-Invariant Skeleton Action Representation Learning via Motion Retargeting,
IJCV(132), No. 7, July 2024, pp. Pages2351-2366.
Springer DOI 2406
BibRef

Yang, D.[Di], Wang, Y.H.[Yao-Hui], Dantcheva, A.[Antitza], Kong, Q.[Quan], Garattoni, L.[Lorenzo], Francesca, G.[Gianpiero], Brémond, F.[François],
LAC: Latent Action Composition for Skeleton-based Action Segmentation,
ICCV23(13633-13644)
IEEE DOI 2401
BibRef

Wang, L.[Lei], Yang, S.M.[Shan-Min], Zhang, J.W.[Jian-Wei], Gu, S.[Song],
2D Human Skeleton Action Recognition Based on Depth Estimation,
IEICE(E108-D), No. 7, July 2024, pp. 869-877.
WWW Link. 2407
BibRef

Yu, B.X.B.[Bruce X. B.], Liu, Y.[Yan], Chan, K.C.C.[Keith C. C.], Chen, C.W.[Chang Wen],
EGCN++: A New Fusion Strategy for Ensemble Learning in Skeleton-Based Rehabilitation Exercise Assessment,
PAMI(46), No. 9, September 2024, pp. 6471-6485.
IEEE DOI 2408
Skeleton, Hidden Markov models, Data models, Ensemble learning, Convolutional neural networks, Training, Human action evaluation, ensemble learning BibRef

Jang, S.J.[Sung-Jun], Lee, H.[Heansung], Kim, W.J.[Woo Jin], Lee, J.[Jungho], Woo, S.[Sungmin], Lee, S.Y.[Sang-Youn],
Multi-Scale Structural Graph Convolutional Network for Skeleton-Based Action Recognition,
CirSysVideo(34), No. 8, August 2024, pp. 7244-7258.
IEEE DOI 2408
Topology, Feature extraction, Correlation, Convolutional neural networks, Convolution, Network topology, link prediction BibRef

Lee, J.[Jungho], Lee, M.[Minhyeok], Lee, D.[Dogyoon], Lee, S.Y.[Sang-Youn],
Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition,
ICCV23(10410-10419)
IEEE DOI Code:
WWW Link. 2401
BibRef

Wang, K.[Kun], Cao, J.X.[Jiu-Xin], Cao, B.W.[Bi-Wei], Liu, B.[Bo],
EnsCLR: Unsupervised skeleton-based action recognition via ensemble contrastive learning of representation,
CVIU(247), 2024, pp. 104076.
Elsevier DOI 2408
Unsupervised representation learning, Contrastive learning, Skeleton-based action recognition BibRef

Hu, R.T.[Ruo-Tong], Wang, X.Z.[Xian-Zhi], Chang, X.J.[Xiao-Jun], Zhang, Y.L.[Yong-Le], Hu, Y.Q.[Ye-Qi], Liu, X.Y.[Xin-Yuan], Yu, S.[Shusong],
CStrCRL: Cross-View Contrastive Learning Through Gated GCN With Strong Augmentations for Skeleton Recognition,
CirSysVideo(34), No. 8, August 2024, pp. 6674-6685.
IEEE DOI Code:
WWW Link. 2408
Skeleton, Task analysis, Logic gates, Semantics, Unsupervised learning, Data models, ST-GGCN BibRef

Wang, L.[Lei], Liu, J.[Jun], Zheng, L.[Liang], Gedeon, T.[Tom], Koniusz, P.[Piotr],
Meet JEANIE: A Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment,
IJCV(132), No. 1, January 2024, pp. 4091-4122.
Springer DOI 2409
BibRef

Zhang, J.X.[Jia-Xu], Tu, Z.G.[Zhi-Gang], Weng, J.[Junwu], Yuan, J.S.[Jun-Song], Du, B.[Bo],
A Modular Neural Motion Retargeting System Decoupling Skeleton and Shape Perception,
PAMI(46), No. 10, October 2024, pp. 6889-6904.
IEEE DOI 2409
Skeleton, Semantics, Geometry, Shape, Training, Logic gates, Geometry perception, motion retargeting, skeleton topology BibRef

Lei, S.Y.[Si-Yue], Tang, B.[Bin], Chen, Y.H.[Yan-Hua], Zhao, M.F.[Ming-Fu], Xu, Y.F.[Yi-Fei], Long, Z.R.[Zou-Rong],
Temporal channel reconfiguration multi-graph convolution network for skeleton-based action recognition,
IET-CV(18), No. 6, 2024, pp. 813-825.
DOI Link 2409
convolution, pose estimation BibRef

Zhang, S.J.[Shao-Jie], Yin, J.Q.[Jian-Qin], Dang, Y.H.[Yong-Hao], Fu, J.J.[Jia-Jun],
SiT-MLP: A Simple MLP With Point-Wise Topology Feature Learning for Skeleton-Based Action Recognition,
CirSysVideo(34), No. 9, September 2024, pp. 8122-8134.
IEEE DOI Code:
WWW Link. 2410
Topology, Network topology, Transformers, Adaptation models, Skeleton, Correlation, spatial-temporal optimization BibRef

Wang, X.H.[Xing-Han], Mu, Y.D.[Ya-Dong],
Localized Linear Temporal Dynamics for Self-Supervised Skeleton Action Recognition,
MultMed(26), 2024, pp. 10189-10199.
IEEE DOI 2410
Skeleton, Feature extraction, Dynamical systems, Task analysis, Aerodynamics, Transforms, Neural networks, contrastive learning BibRef

Cui, R.[Ran], Wu, J.[Jingran], Wang, X.[Xiang],
LG-AKD: Application of a lightweight GCN model based on adversarial knowledge distillation to skeleton action recognition,
JVCIR(104), 2024, pp. 104286.
Elsevier DOI 2411
Action recognition, Adversarial neural networks, GCN, Knowledge distillation, Skeleton BibRef

Liu, Y.N.[Ya-Nan], Li, Y.Q.[Yan-Qiu], Zhang, H.[Hao], Zhang, X.J.[Xue-Jie], Xu, D.[Dan],
Decoupled Knowledge Embedded Graph Convolutional Network for Skeleton-Based Human Action Recognition,
CirSysVideo(34), No. 10, October 2024, pp. 9445-9457.
IEEE DOI 2411
Skeleton, Knowledge engineering, Feature extraction, Computational modeling, Topology, Computational efficiency, knowledge distillation BibRef

Wang, L.[Lei], Zhang, J.W.[Jian-Wei], Yang, W.B.[Wen-Bing], Gu, S.[Song], Yang, S.[Shanmin],
2D human skeleton action recognition with spatial constraints,
IET-CV(18), No. 7, 2024, pp. 968-981.
DOI Link 2411
feature extraction, pattern recognition, video surveillance BibRef

Zhang, F.[Fan], Chongyang, D.[Ding], Liu, K.[Kai], Hong-Jin, L.[Liu],
Multi-scale skeleton simplification graph convolutional network for skeleton-based action recognition,
IET-CV(18), No. 7, 2024, pp. 992-1003.
DOI Link 2411
computer vision, convolution, feature extraction, neural net architecture, neural nets BibRef

Mansouri, A.[Amine], Bakir, T.[Toufik], Elzaar, A.[Abdellah],
Improved semantic-guided network for skeleton-based action recognition,
JVCIR(104), 2024, pp. 104281.
Elsevier DOI 2411
Deep learning, Human Action Recognition (HAR), Convolutional Neural Networks (CNNs), Attention mechanism BibRef

Zhang, W.Y.[Wan-Ying], Liu, M.Y.[Meng-Yuan], Wang, X.[Xinshun], Zhao, S.[Shen], Wang, C.[Can],
CHAMP: A Large-Scale Dataset for Skeleton-Based Composite HumAn Motion Prediction,
CirSysVideo(34), No. 10, October 2024, pp. 10063-10076.
IEEE DOI 2411
Task analysis, Predictive models, Skeleton, Legged locomotion, Training data, Training, Decoding, Human motion prediction, skeleton data BibRef

Zhang, S.Q.[Shan-Qing], Jiao, S.H.[Shu-Heng], Chen, Y.J.[Yu-Jie], Xu, J.Y.[Jia-Yi],
Action recognition algorithm based on skeleton graph with multiple features and improved adjacency matrix,
IET-IPR(18), No. 13, 2024, pp. 4250-4262.
DOI Link 2411
adjacency matrix, graph convolutional networks, human action recognition, multiscale features, skeleton graph, topological relations BibRef


Li, Y.[Yun], Xie, H.[Hao], Xiao, J.[Jun], Zhang, C.[Cong], Liu, T.S.[Tian-Shan], Lam, K.M.[Kin-Man],
Hierarchical Vertex-Wise Intensification Graph Convolution for Skeleton-Based Activity Recognition,
ICIP24(2702-2708)
IEEE DOI 2411
Image recognition, Accuracy, Network topology, Convolution, Graph convolutional networks, Semantics, Activity recognition BibRef

Martinelli, G.[Giulia], Garau, N.[Nicola], Bisagno, N.[Niccolò], Conci, N.[Nicola],
All Skeletons are Created Equal! A Domain Adaptation Transformer to Handle Multiple Topologies,
ICIP24(2716-2722)
IEEE DOI Code:
WWW Link. 2411
Training, Adaptation models, Network topology, Annotations, Transformers, Topology, Skeletons, Poses, Topologies BibRef

Sahbi, H.[Hichem],
One-Shot Multi-Rate Pruning Of Graph Convolutional Networks for Skeleton-Based Recognition,
ICIP24(2445-2451)
IEEE DOI 2411
Training, Image recognition, Accuracy, Graph convolutional networks, Network topology, Task analysis, skeleton-based recognition BibRef

Mitsuzumi, Y.[Yu], Kimura, A.[Akisato], Irie, G.[Go], Nakazawa, A.[Atsushi],
Cross-Action Cross-Subject Skeleton Action Recognition Via Simultaneous Action-Subject Learning with Two-Step Feature Removal,
ICIP24(2182-2186)
IEEE DOI 2411
Training, Image recognition, Accuracy, Target recognition, Data augmentation, Bones, Mutual information, Action Recognition, Disentanglement BibRef

Akremi, M.S.[Mohamed Sanim], Neji, N.[Najett], Tabia, H.[Hedi],
Temporal-Spatial SPDAGG Network For Skeleton-Based Human Action Recognition From Aerial Perspectives,
ICIP24(1384-1390)
IEEE DOI 2411
Face recognition, Autonomous aerial vehicles, Robustness, Behavioral sciences, Human activity recognition, Gauss Aggregation BibRef

Wang, X.S.[Xin-Shun], Fang, Z.B.[Zhong-Bin], Li, X.[Xia], Li, X.T.[Xiang-Tai], Chen, C.[Chen], Liu, M.Y.[Meng-Yuan],
Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learning,
CVPR24(2436-2446)
IEEE DOI 2410
Training, Solid modeling, Silicon carbide, Computational modeling, Pose estimation, Predictive models, in-context learning, skeleton modeling BibRef

Abdelfattah, M.[Mohamed], Hassan, M.[Mariam], Alahi, A.[Alexandre],
MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning,
CVPR24(18678-18687)
IEEE DOI Code:
WWW Link. 2410
Training, Accuracy, Current transformers, Perturbation methods, Semantics, Contrastive learning, Skeleton, contrastive learning BibRef

Noor, N.[Nadhira], Jametoni, F.[Fabianaugie], Kim, J.[Jinbeom], Hong, H.[Hyunsu], Park, I.K.[In Kyu],
Efficient Skeleton-Based Action Recognition for Real-Time Embedded Systems,
MobileAI24(5889-5897)
IEEE DOI 2410
Embedded systems, Accuracy, Quantization (signal), Surveillance, Memory management, Network architecture, Real-time systems, convolutional neural network BibRef

Fukushi, K.[Kenichiro], Nozaki, Y.[Yoshitaka], Nishihara, K.[Kosuke], Nakahara, K.[Kentaro],
Few-shot generative model for skeleton-based human action synthesis using cross-domain adversarial learning,
WACV24(3934-3943)
IEEE DOI 2404
Training, Data visualization, Entropy, Generators, Data models, Adversarial machine learning, Algorithms, Adversarial learning. BibRef

Lerch, D.J.[David J.], Zhong, Z.Y.[Ze-Yun], Martin, M.[Manuel], Voit, M.[Michael], Beyerer, J.[Jürgen],
Unsupervised 3D Skeleton-Based Action Recognition using Cross-Attention with Conditioned Generation Capabilities,
RWSurvil24(202-211)
IEEE DOI 2404
Training, Surveillance, Noise reduction, Noise, Transformers, Skeleton BibRef

Cormier, M.[Mickael], Schmid, Y.[Yannik], Beyerer, J.[Jürgen],
Enhancing Skeleton-Based Action Recognition in Real-World Scenarios Through Realistic Data Augmentation,
RWSurvil24(300-309)
IEEE DOI Code:
WWW Link. 2404
Pose estimation, Data augmentation, Autonomous aerial vehicles, Skeleton, Libraries BibRef

Zhuang, Z.H.[Zhi-Han], Li, Y.[Yuan], Du, S.L.[Song-Lin], Ikenaga, T.[Takeshi],
Intra-frame Skeleton Constraints Modeling and Grouping Strategy Based Multi-Scale Graph Convolution Network for 3D Human Motion Prediction,
MVA23(1-5)
DOI Link 2403
Solid modeling, Convolution, Machine vision, Biological system modeling, Predictive models, Feature extraction BibRef

Zhu, Y.S.[Yi-Sheng], Han, H.[Hu], Yu, Z.T.[Zheng-Tao], Liu, G.C.[Guang-Can],
Modeling the Relative Visual Tempo for Self-supervised Skeleton-based Action Recognition,
ICCV23(13867-13876)
IEEE DOI Code:
WWW Link. 2401
BibRef

Lee, J.[Jungho], Lee, M.[Minhyeok], Cho, S.[Suhwan], Woo, S.[Sungmin], Jang, S.J.[Sung-Jun], Lee, S.Y.[Sang-Youn],
Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition,
ICCV23(10221-10230)
IEEE DOI Code:
WWW Link. 2401
BibRef

Xu, C.X.[Chen-Xin], Tan, R.T.[Robby T.], Tan, Y.H.[Yu-Hong], Chen, S.[Siheng], Wang, X.C.[Xin-Chao], Wang, Y.F.[Yan-Feng],
Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction,
ICCV23(9475-9486)
IEEE DOI Code:
WWW Link. 2401
BibRef

Yan, H.[Hong], Liu, Y.[Yang], Wei, Y.[Yushen], Li, Z.[Zhen], Li, G.B.[Guan-Bin], Lin, L.[Liang],
SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training,
ICCV23(5583-5595)
IEEE DOI Code:
WWW Link. 2401
BibRef

Duan, H.D.[Hao-Dong], Xu, M.Z.[Ming-Ze], Shuai, B.[Bing], Modolo, D.[Davide], Tu, Z.W.[Zhuo-Wen], Tighe, J.[Joseph], Bergamo, A.[Alessandro],
SkeleTR: Towards Skeleton-based Action Recognition in the Wild,
ICCV23(13588-13598)
IEEE DOI 2401
BibRef

Guo, J.W.[Jing-Wen], Liu, H.[Hong], Sun, S.T.[Shi-Tong], Guo, T.Y.[Tian-Yu], Zhang, M.[Min], Si, C.Y.[Chen-Yang],
FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation,
ICCV23(10366-10376)
IEEE DOI 2401
BibRef

Weng, J., Weng, C., Yuan, J.,
Spatio-Temporal Naive-Bayes Nearest-Neighbor (ST-NBNN) for Skeleton-Based Action Recognition,
CVPR17(445-454)
IEEE DOI 1711
Benchmark testing, Image recognition, Skeleton, Videos BibRef

Wang, G.Q.[Guo-Quan], Liu, H.[Hong], Guo, T.Y.[Tian-Yu], Guo, J.W.[Jing-Wen], Wang, T.[Ti], Li, Y.[Yidi],
Self-Supervised 3D Skeleton Representation Learning with Active Sampling and Adaptive Relabeling for Action Recognition,
ICIP23(56-60)
IEEE DOI 2312
BibRef

He, R.[Rong], Tang, Y.S.[Yan-Song], Li, X.[Xiu], Lu, J.W.[Ji-Wen],
Context-Aware Inpainter-Refiner for Skeleton-Based Human Motion Completion,
ICIP23(296-300)
IEEE DOI 2312
BibRef

Wang, L.[Lei], Koniusz, P.[Piotr],
3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition,
CVPR23(5620-5631)
IEEE DOI 2309
BibRef

Lin, L.[Lilang], Zhang, J.H.[Jia-Hang], Liu, J.Y.[Jia-Ying],
Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition,
CVPR23(2363-2372)
IEEE DOI 2309
BibRef

Hachiuma, R.[Ryo], Sato, F.[Fumiaki], Sekii, T.[Taiki],
Unified Keypoint-Based Action Recognition Framework via Structured Keypoint Pooling,
CVPR23(22962-22971)
IEEE DOI 2309
BibRef

Sato, F.[Fumiaki], Hachiuma, R.[Ryo], Sekii, T.[Taiki],
Prompt-Guided Zero-Shot Anomaly Action Recognition using Pretrained Deep Skeleton Features,
CVPR23(6471-6480)
IEEE DOI 2309
BibRef

Wang, X.H.[Xing-Han], Xu, X.[Xin], Mu, Y.D.[Ya-Dong],
Neural Koopman Pooling: Control-Inspired Temporal Dynamics Encoding for Skeleton-Based Action Recognition,
CVPR23(10597-10607)
IEEE DOI 2309
BibRef

Zhou, H.Y.[Huan-Yu], Liu, Q.J.[Qing-Jie], Wang, Y.H.[Yun-Hong],
Learning Discriminative Representations for Skeleton Based Action Recognition,
CVPR23(10608-10617)
IEEE DOI 2309
BibRef

Shah, A.[Anshul], Roy, A.[Aniket], Shah, K.[Ketul], Mishra, S.[Shlok], Jacobs, D.[David], Cherian, A.[Anoop], Chellappa, R.[Rama],
HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions,
CVPR23(18846-18856)
IEEE DOI 2309
BibRef

Deyzel, M.[Michael], Theart, R.P.[Rensu P.],
One-shot skeleton-based action recognition on strength and conditioning exercises,
CVSports23(5169-5178)
IEEE DOI 2309
BibRef

Wang, L.[Lei], Koniusz, P.[Piotr],
Temporal-viewpoint Transportation Plan for Skeletal Few-shot Action Recognition,
ACCV22(IV:307-326).
Springer DOI 2307
BibRef

Zhai, X.L.[Xiao-Lin], Hu, Z.X.[Zheng-Xi], Yang, D.Y.[Ding-Ye], Zhou, L.[Lei], Liu, J.[Jingtai],
Spatial Temporal Network for Image and Skeleton Based Group Activity Recognition,
ACCV22(IV:329-346).
Springer DOI 2307
BibRef

Gao, Z.M.[Zhi-Min], Wang, P.[Peitao], Lv, P.[Pei], Jiang, X.H.[Xiao-Heng], Liu, Q.D.[Qi-Dong], Wang, P.[Pichao], Xu, M.L.[Ming-Liang], Li, W.I.[Wanq-Ing],
Focal and Global Spatial-temporal Transformer for Skeleton-based Action Recognition,
ACCV22(IV:155-171).
Springer DOI 2307
BibRef

Qin, Z.Y.[Zhen-Yue], Ji, P.[Pan], Kim, D.[Dongwoo], Liu, Y.[Yang], Anwar, S.[Saeed], Gedeon, T.[Tom],
Strengthening Skeletal Action Recognizers via Leveraging Temporal Patterns,
RealWorld22(577-593).
Springer DOI 2304
BibRef

Kim, J.[Jaehwan], Lee, J.[Junsuk],
Global Positional Self-Attention for Skeleton-Based Action Recognition,
ICPR22(3355-3361)
IEEE DOI 2212
Visualization, Correlation, Semantics, Gesture recognition, Benchmark testing, Encoding BibRef

Zhu, H.D.[Hai-Dong], Zheng, Z.H.[Zhao-Heng], Nevatia, R.[Ram],
Temporal Shift and Attention Modules for Graphical Skeleton Action Recognition,
ICPR22(3145-3151)
IEEE DOI 2212
Convolution, Shape, Biological system modeling, Skeleton, Kinetic theory, Videos BibRef

Golda, T.[Thomas], Thiemich, J.[Johanna], Cormier, M.[Mickael], Beyerer, J.[Jürgen],
For the Sake of Privacy: Skeleton-Based Salient Behavior Recognition,
ICIP22(3983-3987)
IEEE DOI 2211
Data privacy, Image recognition, Video surveillance, Behavioral sciences, Safety, Task analysis, Anomaly detection, privacy friendly BibRef

Kim, B.[Boeun], Chang, H.J.[Hyung Jin], Kim, J.[Jungho], Choi, J.Y.[Jin Young],
Global-Local Motion Transformer for Unsupervised Skeleton-Based Action Learning,
ECCV22(IV:209-225).
Springer DOI 2211
BibRef

Ma, N.[Ning], Zhang, H.Y.[Hong-Yi], Li, X.[Xuhui], Zhou, S.[Sheng], Zhang, Z.[Zhen], Wen, J.[Jun], Li, H.F.[Hai-Feng], Gu, J.[Jingjun], Bu, J.J.[Jia-Jun],
Learning Spatial-Preserved Skeleton Representations for Few-Shot Action Recognition,
ECCV22(IV:174-191).
Springer DOI 2211
BibRef

Pang, Y.S.[Yun-Sheng], Ke, Q.H.[Qiu-Hong], Rahmani, H.[Hossein], Bailey, J.[James], Liu, J.[Jun],
IGFormer: Interaction Graph Transformer for Skeleton-Based Human Interaction Recognition,
ECCV22(XXV:605-622).
Springer DOI 2211
BibRef

Kwon, T.[Taein], Tekin, B.[Bugra], Tang, S.[Siyu], Pollefeys, M.[Marc],
Context-Aware Sequence Alignment using 4D Skeletal Augmentation,
CVPR22(8162-8172)
IEEE DOI 2210
Training, Pose estimation, Self-supervised learning, Transforms, Transformers, Behavior analysis, Self- semi- meta- Video analysis and understanding BibRef

Chi, H.G.[Hyung-Gun], Ha, M.H.[Myoung Hoon], Chi, S.G.[Seung-Geun], Lee, S.W.[Sang Wan], Huang, Q.X.[Qi-Xing], Ramani, K.[Karthik],
InfoGCN: Representation Learning for Human Skeleton-based Action Recognition,
CVPR22(20154-20164)
IEEE DOI 2210
Representation learning, Convolution, Design methodology, Benchmark testing, Skeleton, Encoding, Representation learning BibRef

Duan, H.D.[Hao-Dong], Zhao, Y.[Yue], Chen, K.[Kai], Lin, D.[Dahua], Dai, B.[Bo],
Revisiting Skeleton-based Action Recognition,
CVPR22(2959-2968)
IEEE DOI 2210
Heating systems, Scalability, Benchmark testing, Feature extraction, Skeleton, Robustness, Action and event recognition BibRef

Salzmann, T.[Tim], Pavone, M.[Marco], Ryll, M.[Markus],
Motron: Multimodal Probabilistic Human Motion Forecasting,
CVPR22(6447-6456)
IEEE DOI 2210
Uncertainty, Computational modeling, Predictive models, Probabilistic logic, Prediction algorithms, Skeleton, Planning, Statistical methods BibRef

Moliner, O.[Olivier], Huang, S.X.[Sang-Xia], Åström, K.[Kalle],
Bootstrapped Representation Learning for Skeleton-Based Action Recognition,
L3D-IVU22(4153-4163)
IEEE DOI 2210
Representation learning, Transfer learning, Pipelines, Self-supervised learning, Cameras, Sampling methods BibRef

Li, T.J.[Tian-Jiao], Ke, Q.H.[Qiu-Hong], Rahmani, H.[Hossein], Ho, R.E.[Rui En], Ding, H.H.[Heng-Hui], Liu, J.[Jun],
Else-Net: Elastic Semantic Network for Continual Action Recognition from Skeleton Data,
ICCV21(13414-13423)
IEEE DOI 2203
Semantics, Skeleton, Task analysis, Action and behavior recognition, Gestures and body pose BibRef

Shi, L.[Lei], Zhang, Y.F.[Yi-Fan], Cheng, J.[Jian], Lu, H.Q.[Han-Qing],
AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition,
ICCV21(13393-13402)
IEEE DOI 2203
Adaptation models, Computational modeling, Process control, Manuals, Skeleton, Data models, Action and behavior recognition, Video analysis and understanding BibRef

Gupta, P.[Pranay], Sharma, D.[Divyanshu], Sarvadevabhatla, R.K.[Ravi Kiran],
Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition,
ICIP21(439-443)
IEEE DOI 2201
Training, Visualization, Image recognition, Syntactics, Skeleton, Task analysis, ZSL, skeleton action recognition, VAE, deep learning, language and vision BibRef

Häring, S.[Simon], Memmesheimer, R.[Raphael], Paulus, D.[Dietrich],
Action Segmentation on Representations of Skeleton Sequences Using Transformer Networks,
ICIP21(3053-3057)
IEEE DOI 2201
Image segmentation, Image recognition, Image coding, Art, Motion segmentation, Estimation, Action segmentation, Transformer, object detection BibRef

Panousis, K.P.[Konstantinos P.], Chatzis, S.[Soritios], Theodoridis, S.[Sergios],
Variational Conditional Dependence Hidden Markov Models for Skeleton-Based Action Recognition,
ISVC21(II:67-80).
Springer DOI 2112
BibRef

Diao, Y.F.[Yun-Feng], Shao, T.J.[Tian-Jia], Yang, Y.L.[Yong-Liang], Zhou, K.[Kun], Wang, H.[He],
BASAR:Black-box Attack on Skeletal Action Recognition,
CVPR21(7593-7603)
IEEE DOI 2111
Activity recognition, Robustness, Data models BibRef

Wang, H.[He], He, F.X.[Fei-Xiang], Peng, Z.X.[Zhe-Xi], Shao, T.J.[Tian-Jia], Yang, Y.L.[Yong-Liang], Zhou, K.[Kun], Hogg, D.[David],
Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack,
CVPR21(14651-14660)
IEEE DOI 2111
Surveillance, Robustness, Autonomous vehicles BibRef

Lu, Z.Z.[Zheng-Zhi], Wang, H.[He], Chang, Z.[Ziyi], Yang, G.[Guoan], Shum, H.P.H.[Hubert P. H.],
Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradient,
ICCV23(4574-4583)
IEEE DOI 2401
BibRef

Lohit, S.[Suhas], Anirudh, R.[Rushil], Turaga, P.[Pavan],
Recovering Trajectories of Unmarked Joints in 3D Human Actions Using Latent Space Optimization,
WACV21(2341-2350)
IEEE DOI 2106
Manifolds, Tracking, Time series analysis, Training data, Transforms, Trajectory BibRef

Yang, D.[Di], Dai, R.[Rui], Wang, Y.[Yaohui], Mallick, R.[Rupayan], Minciullo, L.[Luca], Francesca, G.[Gianpiero], Brémond, F.[François],
Selective Spatio-Temporal Aggregation Based Pose Refinement System: Towards Understanding Human Activities in Real-World Videos,
WACV21(2362-2371)
IEEE DOI 2106
Pose estimation, Boosting, Skeleton, Data models BibRef

Cai, J.M.[Jin-Miao], Jiang, N.[Nianjuan], Han, X.G.[Xiao-Guang], Jia, K.[Kui], Lu, J.B.[Jiang-Bo],
JOLO-GCN: Mining Joint-Centered Light-Weight Information for Skeleton-Based Action Recognition,
WACV21(2734-2743)
IEEE DOI 2106
Visualization, Skeleton, Character recognition, Optical flow BibRef

Obinata, Y.[Yuya], Yamamoto, T.[Takuma],
Temporal Extension Module for Skeleton-Based Action Recognition,
ICPR21(534-540)
IEEE DOI 2105
Convolution, Biological system modeling, Feature extraction, Skeleton, Optimization, Action recognition, Kinetics-Skeleton BibRef

Chen, L.[Lian], Lu, K.[Ke], Gao, P.C.[Peng-Cheng], Xue, J.[Jian], Wang, J.B.[Jin-Bao],
A Novel Multi-feature Skeleton Representation for 3d Action Recognition,
IUC20(365-379).
Springer DOI 2103
BibRef

Radek, S.,
Skeleton Action Recognition Based on Singular Value Decomposition,
ICIP20(1831-1835)
IEEE DOI 2011
Protocols, Skeleton, Symmetric matrices, Robustness, Trajectory, Feature extraction, singular value decomposition BibRef

Singh, I., Zhu, X., Greenspan, M.,
Multi-Modal Fusion With Observation Points For Skeleton Action Recognition,
ICIP20(1781-1785)
IEEE DOI 2011
Joints, Bones, Training, multimodal fusion BibRef

Su, K., Liu, X., Shlizerman, E.,
PREDICT CLUSTER: Unsupervised Skeleton Based Action Recognition,
CVPR20(9628-9637)
IEEE DOI 2008
Decoding, Skeleton, Training, Task analysis, Cameras BibRef

Zhang, X., Xu, C., Tao, D.,
Context Aware Graph Convolution for Skeleton-Based Action Recognition,
CVPR20(14321-14330)
IEEE DOI 2008
Convolution, Context-aware services, Computational modeling, Context modeling, Task analysis, Skeleton, Feature extraction BibRef

Yang, Z., Zhu, W., Wu, W., Qian, C., Zhou, Q., Zhou, B., Loy, C.C.,
TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting,
CVPR20(5305-5314)
IEEE DOI 2008
Skeleton, Perturbation methods, Rendering (computer graphics), Decoding BibRef

Cui, Q., Sun, H., Yang, F.,
Learning Dynamic Relationships for 3D Human Motion Prediction,
CVPR20(6518-6526)
IEEE DOI 2008
Skeleton, Training, Adaptation models, Predictive models, Solid modeling, Dynamics BibRef

Wang, Y., Xiao, Y., Xiong, F., Jiang, W., Cao, Z., Zhou, J.T., Yuan, J.,
3DV: 3D Dynamic Voxel for Action Recognition in Depth Video,
CVPR20(508-517)
IEEE DOI 2008
Machine learning, Dynamics, Solid modeling, Skeleton BibRef

Raj, N.B.[N. Bharath], Subramanian, A.[Anand], Ravichandran, K.[Kashyap], Venkateswaran, N.,
Exploring Techniques to Improve Activity Recognition using Human Pose Skeletons,
WACVWS20(165-172)
IEEE DOI 2006
Skeleton, Feature extraction, Activity recognition, Mathematical model, Robustness, Pose estimation, Training BibRef

Zhao, R., Wang, K., Su, H., Ji, Q.,
Bayesian Graph Convolution LSTM for Skeleton Based Action Recognition,
ICCV19(6881-6891)
IEEE DOI 2004
Bayes methods, feature extraction, graph theory, image motion analysis, image representation, Kernel BibRef

Szczapa, B., Daoudi, M., Berretti, S., del Bimbo, A., Pala, P., Massart, E.,
Fitting, Comparison, and Alignment of Trajectories on Positive Semi-Definite Matrices with Application to Action Recognition,
HBU19(1241-1250)
IEEE DOI 2004
curve fitting, feature extraction, image motion analysis, image representation, image sequences, Skeleton BibRef

Hakim, T., Shimshoni, I.,
A-MAL: Automatic Motion Assessment Learning from Properly Performed Motions in 3D Skeleton Videos,
CVPM19(1589-1598)
IEEE DOI 2004
image motion analysis, image segmentation, learning (artificial intelligence), medical image processing, fma BibRef

Kao, J., Ortega, A., Tian, D., Mansour, H., Vetro, A.,
Graph Based Skeleton Modeling for Human Activity Analysis,
ICIP19(2025-2029)
IEEE DOI 1910
Human activity analysis, graph-based representation, motion capture data, 3D action recognition BibRef

Tang, Y.S.[Yan-Song], Tian, Y.[Yi], Lu, J.W.[Ji-Wen], Li, P.Y.[Pei-Yang], Zhou, J.[Jie],
Deep Progressive Reinforcement Learning for Skeleton-Based Action Recognition,
CVPR18(5323-5332)
IEEE DOI 1812
Joints, Videos, Biological system modeling BibRef

Cui, R., Zhu, A., Zhang, S., Hua, G.,
Multi-source Learning for Skeleton-based Action Recognition Using Deep LSTM Networks,
ICPR18(547-552)
IEEE DOI 1812
Skeleton, Logic gates, Computational modeling, Torso, Legged locomotion, Cameras, Data mining, Machine Learning, Long Short-Term Memory BibRef

Khodabandeh, M., Joze, H.R.V., Zharkov, I., Pradeep, V.,
DIY Human Action Dataset Generation,
Joint18(1529-152910)
IEEE DOI 1812
Skeleton, Task analysis, Trajectory, Generators, Training BibRef

Hiraoka, Y.[Yutaro], Fukui, K.[Kazuhiro],
Deep Randomized Time Warping for Action Recognition,
MVA23(1-5)
DOI Link 2403
Machine vision, Dynamics, Feature extraction, Pattern matching BibRef

Sogi, N., Fukui, K.,
Action Recognition Method Based on Sets of Time Warped ARMA Models,
ICPR18(1773-1778)
IEEE DOI 1812
Observability, Hidden Markov models, Analytical models, Manifolds, Skeleton, Solid modeling BibRef

Xu, J., Tasaka, K., Yanagihara, H.,
Beyond Two-stream: Skeleton-based Three-stream Networks for Action Recognition in Videos,
ICPR18(1567-1573)
IEEE DOI 1812
Skeleton, Videos, Optical imaging, Agriculture BibRef

Demisse, G.G., Papadopoulos, K., Aouada, D., Ottersten, B.,
Pose Encoding for Robust Skeleton-Based Action Recognition,
Crowd18(301-3016)
IEEE DOI 1812
Noise measurement, Data models, Decoding, Cameras, Noise reduction, Training, Unsupervised learning BibRef

Simkanic, R.[Radek],
Matrix Descriptor of Changes (MDC): Activity Recognition Based on Skeleton,
ACIVS18(14-25).
Springer DOI 1810
BibRef

Wang, Z.K.[Zhi-Kai], Zhang, C.Y.[Chong-Yang], Luo, W.[Wu], Lin, W.Y.[Wei-Yao],
Key Joints Selection and Spatiotemporal Mining for Skeleton-Based Action Recognition,
ICIP18(3458-3462)
IEEE DOI 1809
Histograms, Trajectory, Spatiotemporal phenomena, Skeleton, Encoding, Feature extraction, skeleton BibRef

Tsingalis, I., Vretos, N., Daras, P.,
Leveraging Skeleton Structure and Time Dependencies in the Scope of Action Recognition,
ICIP18(470-474)
IEEE DOI 1809
Skeleton, Feature extraction, Optimization, Standards, Noise measurement, Human Activity BibRef

Das, S., Koperski, M., Bremond, F., Francesca, G.,
Action recognition based on a mixture of RGB and depth based skeleton,
AVSS17(1-6)
IEEE DOI 1806
CAD, feature extraction, image colour analysis, image recognition, learning (artificial intelligence), neural nets, Videos BibRef

Liu, M., He, Q., Liu, H.,
Fusing shape and motion matrices for view invariant action recognition using 3D skeletons,
ICIP17(3670-3674)
IEEE DOI 1803
Encoding, Matrix converters, Robustness, Shape, Skeleton, Training, 3D action recognition, skeleton sequence BibRef

Papadopoulos, K., Antunes, M., Aouada, D., Ottersten, B.,
Enhanced trajectory-based action recognition using human pose,
ICIP17(1807-1811)
IEEE DOI 1803
Computational modeling, Feature extraction, Heating systems, Histograms, Skeleton, Standards, Trajectory, Action recognition, spatio-temporal features BibRef

Lee, I., Kim, D., Kang, S., Lee, S.,
Ensemble Deep Learning for Skeleton-Based Action Recognition Using Temporal Sliding LSTM Networks,
ICCV17(1012-1020)
IEEE DOI 1802
feature extraction, image motion analysis, image recognition, image representation, learning (artificial intelligence), BibRef

Wang, P.[Pei], Yuan, C.F.[Chun-Feng], Hu, W.M.[Wei-Ming], Li, B.[Bing], Zhang, Y.N.[Yan-Ning],
Graph Based Skeleton Motion Representation and Similarity Measurement for Action Recognition,
ECCV16(VII: 370-385).
Springer DOI 1611
BibRef

Ubalde, S., Gómez-Fernández, F., Goussies, N.A., Mejail, M.,
Skeleton-based action recognition using Citation-kNN on bags of time-stamped pose descriptors,
ICIP16(3051-3055)
IEEE DOI 1610
Hafnium BibRef

Mavroudi, E., Bhaskara, D., Sefati, S., Ali, H., Vidal, R.,
End-to-End Fine-Grained Action Segmentation and Recognition Using Conditional Random Field Models and Discriminative Sparse Coding,
WACV18(1558-1567)
IEEE DOI 1806
feature extraction, gesture recognition, image classification, image representation, image segmentation, Task analysis BibRef

Batabyal, T.[Tamal], Chattopadhyay, T.[Tanushyam], Mukherjee, D.P.[Dipti Prasad],
Action recognition using joint coordinates of 3D skeleton data,
ICIP15(4107-4111)
IEEE DOI 1512
Covariance; Kinect; Local Linear Embedding BibRef

Meshry, M., Hussein, M.E.[Mohamed E.], Torki, M.[Marwan],
Linear-time online action detection from 3D skeletal data using bags of gesturelets,
WACV16(1-9)
IEEE DOI 1606
Feature extraction BibRef

Sharaf, A.[Amr], Torki, M.[Marwan], Hussein, M.E.[Mohamed E.], El-Saban, M.[Motaz],
Real-Time Multi-scale Action Detection from 3D Skeleton Data,
WACV15(998-1005)
IEEE DOI 1503
Detectors BibRef

Evangelidis, G.[Georgios], Singh, G.[Gurkirt], Horaud, R.[Radu],
Skeletal Quads: Human Action Recognition Using Joint Quadruples,
ICPR14(4513-4518)
IEEE DOI 1412
Accuracy; Joints; Kernel; Training; Vectors BibRef

Chaudhry, R.[Rizwan], Ofli, F.[Ferda], Kurillo, G.[Gregorij], Bajcsy, R.[Ruzena], Vidal, R.[Rene],
Bio-inspired Dynamic 3D Discriminative Skeletal Features for Human Action Recognition,
HAU3D13(471-478)
IEEE DOI 1309
BibRef

Bakken, R.H.[Rune Havnung], Hilton, A.[Adrian],
Real-Time Pose Estimation Using Constrained Dynamics,
AMDO12(37-46).
Springer DOI 1208
BibRef

Bakken, R.H., Eliassen, L.M.,
Real-time 3D skeletonisation in computer vision-based human pose estimation using GPGPU,
IPTA12(61-67)
IEEE DOI 1503
graphics processing units BibRef

Karali, A.[Abubakrelsedik], El Helw, M.[Mohamed],
Motion History of Skeletal Volumes for Human Action Recognition,
ISVC12(II: 135-144).
Springer DOI 1209
BibRef

Xu, R.[Ran], Agarwal, P.[Priyanshu], Kumar, S.[Suren], Krovi, V.N.[Venkat N.], Corso, J.J.[Jason J.],
Combining Skeletal Pose with Local Motion for Human Activity Recognition,
AMDO12(114-123).
Springer DOI 1208
BibRef

Yoon, S.M.[Sang Min], Kuijper, A.[Arjan],
Human Action Recognition Using Segmented Skeletal Features,
ICPR10(3740-3743).
IEEE DOI 1008
BibRef
And:
3D Human Action Recognition Using Model Segmentation,
ICIAR10(I: 189-199).
Springer DOI 1006
BibRef

Chapter on Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities continues in
Human Action Recognition, Neural Nets for Skeletal Representations .


Last update:Nov 26, 2024 at 16:40:19