Multi-Granularity Anchor-Contrastive Representation Learning for Semi-Supervised Skeleton-Based Action Recognition
The DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index.
Abstract
In the semi-supervised skeleton-based action recognition task, obtaining more discriminative information from both labeled and unlabeled data is a challenging problem. As the current mainstream approach, contrastive learning can learn more representations of augmented data, which can be considered as the pretext task of action recognition. However, such a method still confronts three main limitations: 1) It usually learns global-granularity features that cannot well reflect the local motion information. 2) The positive/negative pairs are usually pre-defined, some of which are ambiguous. 3) It generally measures the distance between positive/negative pairs only within the same granularity, which neglects the contrasting between the cross-granularity positive and negative pairs. Toward these limitations, we propose a novel Multi-granularity Anchor-Contrastive representation Learning (dubbed as MAC-Learning) to learn multi-granularity representations by conducting inter- and intra-granularity contrastive pretext tasks on the learnable and structural-link skeletons among three types of granularities covering local, context, and global views. To avoid the disturbance of ambiguous pairs from noisy and outlier samples, we design a more reliable Multi-granularity Anchor-Contrastive Loss (dubbed as MAC-Loss) that measures the agreement/disagreement between high-confidence soft-positive/negative pairs based on the anchor graph instead of the hard-positive/negative pairs in the conventional contrastive loss. Extensive experiments on both NTU RGB+D and Northwestern-UCLA datasets show that the proposed MAC-Learning outperforms existing competitive methods in semi-supervised skeleton-based action recognition tasks.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Momentum Contrast for Unsupervised Visual Representation Learning
He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00975 · Cited by 13,347
Learning 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
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Carreira, J., & Zisserman, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.502 · Cited by 9,570
Realtime 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 2×
“Meanwhile, skeleton sequences can be easily obtained by depth sensors or pose estimation algorithms [20], [21].”
BackgroundMethodSpatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
Yan, S., Xiong, Y., & Lin, D. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12328 · Cited by 5,410 · cited 6×
“It is noted that all comparative methods adopt 2.8 19.2 ST-GCN [13] 3.1 16.7 MS-G3D [31] 6.4 98.0 2s-AGCN [29] 6.9 37.4 AS-GCN [14] 7.2 35.5 2s-AAGCN [35] 7.6 39.1 DGNN [80] 8.1 71.1 DeCoup-GCN [81] 13.7 102.3 MAC-Learning (Ours) 8.1 40.7 The abbreviations “M” and “G” denote Mega and Giga,…”
BackgroundMethodInfluentialBootstrap Your Own Latent: A New Approach to Self-Supervised Learning
Grill, J.-B., Strub, F., Altché, F., Tallec, C., Richemond, P. H., Buchatskaya, E., Doersch, C., Pires, B. A., Guo, Z. D., Azar, M. G., et al. (2020) · arXiv · doi:10.48550/arxiv.2006.07733 · Cited by 3,846 · cited 1×
“In recent years, contrastive learning has attracted considerable attention [63], [64], [65], [66], [67].”
BackgroundAction Recognition with Improved Trajectories
Wang, H., & Schmid, C. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.441 · Cited by 3,407
NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis
Shahroudy, A., Liu, J., Ng, T.-T., & Wang, G. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.115 · Cited by 3,148
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., & Joulin, A. (2020) · arXiv · doi:10.48550/arxiv.2006.09882 · Cited by 2,499
A survey on vision-based human action recognition
Poppe, R. (2010) · Image and Vision Computing · doi:10.1016/j.imavis.2009.11.014 · Cited by 2,242
Tian, Y., Krishnan, D., & Isola, P. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58621-8_45 · Cited by 1,997
Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN
Li, S., Li, W., Cook, C., Zhu, C., & Gao, Y. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00572 · Cited by 972
A New Representation of Skeleton Sequences for 3D Action Recognition
Ke, Q., Bennamoun, M., An, S., Sohel, F., & Boussaid, F. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.486 · Cited by 793 · cited 2×
“To learn the discriminative representations of skeletons, some deep learning-based methods achieve remarkable performance by designing various Convolutional Neural Networks (CNN) or Recurrent Neural Networks (RNN) [22], [24], [26], [27].”
BackgroundZhang, P., Lan, C., Xing, J., Zeng, W., Xue, J., & Zheng, N. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.233 · Cited by 691 · cited 2×
“Several previous works [23], [64], [79] have validated that view-invariant structures can help improving the recognition performance.”
BackgroundOn Variational Bounds of Mutual Information
Poole, B., Ozair, S., Oord, A. V. D., Alemi, A. A., & Tucker, G. (2019) · arXiv · doi:10.48550/arxiv.1905.06922 · Cited by 480 · cited 1×
“Overall, the core of contrastive loss [69] is to enforce the feature consistency between query and positive samples, and the discrimination between query and negative samples by calculating the distance between sample representations.”
BackgroundDecoupling GCN with DropGraph Module for Skeleton-Based Action Recognition
Cheng, K., Zhang, Y., Cao, C., Shi, L., Cheng, J., & Lu, H. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58586-0_32 · Cited by 384
Spatiotemporal Co-Attention Recurrent Neural Networks for Human-Skeleton Motion Prediction
Shu, X., Zhang, L., Qi, G.-J., Liu, W., & Tang, J. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3050918 · Cited by 276
Self-citation3D Human Action Representation Learning via Cross-View Consistency Pursuit
Li, L., Wang, M., Ni, B., Wang, H., Yang, J., & Zhang, W. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00471 · Cited by 236 · cited 7×
“In the data preparation phase, all skeleton sequences are temporally resized to the fixed-length T ¼ 50 frames by linear interpolation for both NTU RGB+D and NW-UCLA data-sets, which is similar to [34].”
BackgroundMethodInfluentialRao, H., Xu, S., Hu, X., Cheng, J., & Hu, B. (2021) · Information Sciences · doi:10.1016/j.ins.2021.04.023 · Cited by 235
MS2L: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognition
Lin, L., Song, S., Yang, W., & Liu, J. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413548 · Cited by 223 · cited 7×
“Recently, some contrastive representation learning meth-ods have shown remarkable performance for either unsupervised or self-supervised skeleton-based action recognition tasks [32], [33], [34], [55], [57], [58], [60].”
BackgroundMethodInfluentialA large-scale study on unsupervised spatiotemporal representation learning
Feichtenhofer, C., Fan, H., Xiong, B., Girshick, R., & He, K. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00331 · Cited by 222
Unsupervised Representation Learning With Long-Term Dynamics for Skeleton Based Action Recognition
Zheng, N., Wen, J., Liu, R., Long, L., Dai, J., & Gong, Z. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11853 · Cited by 201 · cited 3×
“…representative methods, including semi-supervised methods (e.g., S 4 L [73], Pseudolabels [74], VAT [75], VAT+EntMin [76], ASSL [48]), and unsupervised methods (e.g., AS-CAL [32], LongT GAN [53], Holden et al. [77], EnGAN-PoseRNN [54], MS 2 L [55], Skeleton-Contrastive [58], and 3s-CrosSCLR [34]).”
BackgroundMethodUnsupervised Feature Learning of Human Actions As Trajectories in Pose Embedding Manifold
Kundu, J. N., Gor, M., Uppala, P. K., & Radhakrishnan, V. B. (2019) · 2019 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2019.00160 · Cited by 72
Chen, T., Wang, Z., Li, L., Li, D., Li, Z., Chang, X., Bian, P., Liang, G., Wang, Q., & Xie, T. (2025) · Schloss Dagstuhl – Leibniz-Zentrum für Informatik · doi:10.4230/lipics.ecoop.2025.6
Metadata
- Authors
- Shu, X., Xu, B., Zhang, L., & Tang, J.
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2023-06-01
- Volume
- 45
- Issue
- 6
- Pages
- 7559-7576
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W4309368547
- Cited by
- 159
- References
- 25
- FWCI
- 11.33
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.