Self-supervised Skeleton-based Action Recognition

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

2 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

21 shown of 21 papers with code (30 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition
  15 Jul 2023 2 repositories listed
  Inspired by SkeletonBYOL, this paper further presents a Cross-Model and Cross-Stream (CMCS) framework.
• Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition
  1 Aug 2020 2 repositories listed Syntology ran 2 of 11 samples · 9 unverified
  In this paper, we for the first time propose a contrastive action learning paradigm named AS-CAL that can leverage different augmentations of unlabeled skeleton data to learn action representations in an unsupervised…
• Spatial Hierarchy and Temporal Attention Guided Cross Masking for Self-supervised Skeleton-based Action Recognition
  26 Sep 2024 1 repository listed
  In self-supervised skeleton-based action recognition, the mask reconstruction paradigm is gaining interest in enhancing model refinement and robustness through effective masking.
• Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition
  23 Sep 2024 1 repository listed
  Inspired by SkeletonBYOL, this paper further presents a Cross-Model and Cross-Stream (CMCS) framework.
• STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences
  15 Jul 2024 1 repository listed
  Self-supervised pretraining methods with masked prediction demonstrate remarkable within-dataset performance in skeleton-based action recognition.
• Exploring Self-supervised Skeleton-based Action Recognition in Occluded Environments
  21 Sep 2023 1 repository listed
  IosPSTL combines a cluster-agnostic KNN imputer with an Occluded Partial Spatio-Temporal Learning (OPSTL) strategy.
• Masked Motion Predictors are Strong 3D Action Representation Learners
  14 Aug 2023 1 repository listed Syntology ran 3 of 4 samples · 1 unverified · 4 pointer-only (licence)
  To be specific, the proposed MAMP takes as input the masked spatio-temporal skeleton sequence and predicts the corresponding temporal motion of the masked human joints.
• SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training
  17 Jul 2023 1 repository listed
  Moreover, these methods ignore how to utilize the fine-grained dependencies among different skeleton joints to pre-train an efficient skeleton sequence learning model that can generalize well across different datasets.
• Part Aware Contrastive Learning for Self-Supervised Action Recognition
  1 May 2023 1 repository listed Syntology ran 6 of 12 samples · 6 unverified · 12 pointer-only (licence)
  This paper proposes an attention-based contrastive learning framework for skeleton representation learning, called SkeAttnCLR, which integrates local similarity and global features for skeleton-based action…
• HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions
  1 Apr 2023 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  In this work, we propose a new contrastive learning approach to train models for skeleton-based action recognition without labels.
• Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences
  17 Feb 2023 1 repository listed Syntology ran 3 of 5 samples · 2 unverified
  Specifically, we construct a negative-sample-free triplet steam structure that is composed of an anchor stream without any masking, a spatial masking stream with Central Spatial Masking (CSM), and a temporal masking…
• Modeling the Relative Visual Tempo for Self-supervised Skeleton-based Action Recognition
  1 Jan 2023 1 repository listed
  Specifically, we design a Relative Visual Tempo Learning (RVTL) task to explore the motion information in intra-video clips, and an Appearance-Consistency (AC) task to learn appearance information simultaneously,…
• Hierarchical Contrast for Unsupervised Skeleton-based Action Representation Learning
  5 Dec 2022 1 repository listed
  This paper targets unsupervised skeleton-based action representation learning and proposes a new Hierarchical Contrast (HiCo) framework.
• Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentations
  24 Nov 2022 1 repository listed
  In this paper, we investigate the potential of adopting strong augmentations and propose a general hierarchical consistent contrastive learning framework (HiCLR) for skeleton-based action recognition.
• CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation
  26 Aug 2022 1 repository listed
  In this work, we formulate the cross-modal interaction as a bidirectional knowledge distillation problem.
• Contrastive Learning from Spatio-Temporal Mixed Skeleton Sequences for Self-Supervised Skeleton-Based Action Recognition
  7 Jul 2022 1 repository listed
  First, SkeleMix utilizes the topological information of skeleton data to mix two skeleton sequences by randomly combing the cropped skeleton fragments (the trimmed view) with the remaining skeleton sequences (the…
• Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition
  7 Dec 2021 1 repository listed
  In this paper, to make better use of the movement patterns introduced by extreme augmentations, a Contrastive Learning framework utilizing Abundant Information Mining for self-supervised action Representation (AimCLR)…
• Skeleton-Contrastive 3D Action Representation Learning
  8 Aug 2021 1 repository listed Syntology ran 4 of 7 samples · 3 unverified · 7 pointer-only (licence)
  In particular, we propose inter-skeleton contrastive learning, which learns from multiple different input skeleton representations in a cross-contrastive manner.
• 3D Human Action Representation Learning via Cross-View Consistency Pursuit
  29 Apr 2021 1 repository listed Syntology ran 2 of 2 samples · 0 unverified · 1 pointer-only (licence)
  In this work, we propose a Cross-view Contrastive Learning framework for unsupervised 3D skeleton-based action Representation (CrosSCLR), by leveraging multi-view complementary supervision signal.
• Unsupervised 3D Human Pose Representation with Viewpoint and Pose Disentanglement
  14 Jul 2020 1 repository listed
  Learning a good 3D human pose representation is important for human pose related tasks, e.
• PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition
  27 Nov 2019 1 repository listed
  Given inputs of body keypoints sequences obtained during various movements, our system associates the sequences with actions.

Syntology lines on 7 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.