The DOI matches its Crossref record; 31 of the 32 references it cites were found in a registry or an index.
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
Open accessAbstract
Dynamics of human body skeletons convey significant information for human action recognition. Conventional approaches for modeling skeletons usually rely on hand-crafted parts or traversal rules, thus resulting in limited expressive power and difficulties of generalization. In this work, we propose a novel model of dynamic skeletons called Spatial-Temporal Graph Convolutional Networks (ST-GCN), which moves beyond the limitations of previous methods by automatically learning both the spatial and temporal patterns from data. This formulation not only leads to greater expressive power but also stronger generalization capability. On two large datasets, Kinetics and NTU-RGBD, it achieves substantial improvements over mainstream methods.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“In tasks such as image object recognition, the hierarchical representation and locality are usually achieved by the intrinsic properties of convolutional neural networks (Krizhevsky, Sutskever, and Hinton 2012), rather than manually assigning object parts.”
MethodSemi-supervised classification with graph convolutional networks
Kipf, T. N., & Welling, M. (2016) · arXiv · doi:10.48550/arxiv.1609.02907 · Cited by 24,853 · cited 8×
“In the single frame case, ST-GCN with the first partitioning strategy can be implemented with the following formula (Kipf and Welling 2017) where Here the weight vectors of multiple output channels are stacked to form the weight matrix W .”
BackgroundMethodInfluentialLearning Spatiotemporal Features with 3D Convolutional Networks
Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.510 · Cited by 9,593 · cited 2×
“In general, human action can be recognized from multiple modalities(Simonyan and Zisserman 2014; Tran et al. 2015; Wang, Qiao, and Tang 2015; Wang et al. 2016; Zhao et al. 2017), such as appearance, depth, optical flows, and body skeletons (Du, Wang, and Wang 2015; Liu et al.”
BackgroundRealtime Multi-person 2D Pose Estimation Using Part Affinity Fields
Cao, Z., Simon, T., Wei, S.-E., & Sheikh, Y. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.143 · Cited by 7,539 · cited 3×
“Skeleton and joint trajectories of human bodies are robust to illumination change and scene variation, and they are easy to obtain owing to the highly accurate depth sensors or pose estimation algorithms (Shotton et al. 2011; Cao et al. 2017a).”
BackgroundMethodDeformable Convolutional Networks
Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., & Wei, Y. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.89 · Cited by 7,513 · cited 1×
“More detailed explanation and other applications of this formulation can be found in (Dai et al. 2017).”
BackgroundSelf-citationAdvances In Deep Learning On Graphs (Gsp'18 Workshop)Preprint
Defferrard, M., Bresson, X., & Vandergheynst, P. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.09375 · Cited by 7,021 · cited 2×
“…graphs of arbitrary structures, have received increasing attention and successfully been adopted in a number of applications, such as image classification (Bruna et al. 2014), document classifi-cation (Defferrard, Bresson, and Vandergheynst 2016), and semi-supervised learning (Kipf and Welling 2017).”
BackgroundTwo-Stream Convolutional Networks for Action Recognition in Videos
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1406.2199 · Cited by 6,756 · cited 1×
“In general, human action can be recognized from multiple modalities(Simonyan and Zisserman 2014; Tran et al. 2015; Wang, Qiao, and Tang 2015; Wang et al. 2016; Zhao et al. 2017), such as appearance, depth, optical flows, and body skeletons (Du, Wang, and Wang 2015; Liu et al. 2016).”
BackgroundThe Kinetics Human Action Video DatasetPreprint
Kay, W., Carreira, J., Simonyan, K., Zhang, B., Hillier, C., Vijayanarasimhan, S., Viola, F., Green, T., Back, T., Natsev, P., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.06950 · Cited by 5,004 · cited 13×
“Weevaluate the recognition performance by top-1 and top-5 classification accuracy as recommended by the dataset authors (Kay et al. 2017).”
BackgroundMethodInfluentialTemporal Segment Networks: Towards Good Practices for Deep Action Recognition
Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., & Gool, L. V. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46484-8_2 · Cited by 4,232 · cited 4×
“We train the standard TSN (Wang et al. 2016) models from scratches on Kinetics with RGB and optical flow models.”
BackgroundMethodInfluentialSelf-citationSpectral Networks and Locally Connected Networks on Graphs
Bruna, J., Zaremba, W., Szlam, A., & LeCun, Y. (2013) · arXiv · doi:10.48550/arxiv.1312.6203 · Cited by 3,983
Research works printed but not linked: 4
- [Cao et al. 2017b] Cao, Z.; Simon, T.; Wei, S.-E.; and Sheikh, Y. 2017b. Realtime multi-person 2d pose estimation using part affinity fields. In CVPR .
- [Defferrard, Bresson, and Vandergheynst 2016] Defferrard, M.; Bresson, X.; and Vandergheynst, P. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. In NIPS .
- [Hussein et al. 2013] Hussein, M. E.; Torki, M.; Gowayyed, M. A.; and El-Saban, M. 2013. Human action recognition using a temporal hierarchy of covariance descriptors on 3d joint locations. In IJCAI .
- [Wang et al. 2012] Wang, J.; Liu, Z.; Wu, Y.; and Yuan, J. 2012. Mining actionlet ensemble for action recognition with depth cameras. In CVPR . IEEE.
Cited by
Sorted by citations
Items 1,001–1,007 of 1,007
Keypoint Message Passing for Video-based Person Re-Identification
Chen, D., Doering, A., Zhang, S.-S., Yang, J., Gall, J., & Schiele, B. (2021) · AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i1.19899 · Cited by 26
“Following (Yan, Xiong, and Lin 2018) and (Li, Zhao, and Ma 2020), we represent a sequence of person joints with a spatial-temporal graph G = ( V, E ) .”
BackgroundMethodTeaching Chinese Sign Language with a Smartphone
Zhang, Y., Min, Y.-C., & Chen, X.-L. (2021) · Virtual Reality & Intelligent Hardware · doi:10.1016/j.vrih.2021.05.004 · Cited by 26
Kwon, H., Clifford, G. D., Genias, I., Bernhard, D., Esper, C. D., Factor, S. A., & McKay, J. L. (2023) · Sensors · doi:10.3390/s23041766 · Cited by 24
“We also compared the proposed model to several deep learning models for processing human skeleton time-series, including Temporal convolutional network (TCN) [52], Graphical convolutional network (GCN) [53], GCN with attention model (AGCN) [34], and AGCN with Adaptive Trimming (AT+AGCN).”
ResultUniMTS: Unified Pre-training for Motion Time Series
Zhang, X., Teng, D., Chowdhury, R. R., Li, S., Hong, D., Gupta, R. K., & Shang, J. (2024) · arXiv · Cited by 9
“Specifically, we freeze the text encoder f θ and update weights of the graph encoder g ϕ followed by a linear classifier h ψ .”
UniMTS: Unified Pre-training for Motion Time Series
Zhang, X., Teng, D., Chowdhury, R., Li, S., Hong, D., Gupta, R., & Shang, J. (2024) · Advances in Neural Information Processing Systems 37 · doi:10.52202/079017-3414 · Cited by 8
View Enhanced Jigsaw Puzzle for Self-Supervised Feature Learning in 3D Human Action Recognition
You, W., & Wang, X. (2022) · IEEE Access · doi:10.1109/access.2022.3165040 · Cited by 6
Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition
Qiu, H., Hou, B., Ren, B., & Zhang, X. (2022) · arXiv · doi:10.48550/arxiv.2201.02849 · Cited by 44
“Compared with the GCN-based methods [38,27,25,5,39,20,4], our method has certain advantages.”
Method
Metadata
- Authors
- Yan, S., Xiong, Y., & Lin, D.
- Affiliations
- Chinese University of Hong Kong (HK)
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2018-04-27
- Volume
- 32
- Issue
- 1
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W2963076818
- Cited by
- 5,410
- References
- 32
- Citations by year
- 2026: 552 · 2025: 895 · 2024: 915 · 2023: 915 · 2022: 755 · 2021: 742 · 2020: 414 · 2019: 193 · 2018: 29
- FWCI
- 103.84
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Proceedings of the AAAI Conference on Artificial Intelligence (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Chinese University of Hong Kong
- SenseTime Group
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Physical Sciences › Computer Science › Human-Computer Interaction › Hand Gesture Recognition Systems
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Human Motion and Animation
- Keywords
- skeleton-based action recognition, spatio-temporal graph convolutional network, graph convolutional networks, temporal modeling, spatial modeling, generalization
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
