STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences

• URL: http://arxiv.org/abs/2407.10935v2
• Date: Sun, 09 Nov 2025 17:15:02 GMT
• Title: STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences
• Abstract summary: Self-supervised pretraining methods with masked prediction demonstrate remarkable within-dataset performance in skeleton-based action recognition.<n>Unlike contrastive learning approaches, they do not produce well-separated clusters.<n>We propose Self-supervised Tuning for 3D Action Recognition in Skeleton sequences (STARS)
• Score: 2.1139217176397334
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-supervised pretraining methods with masked prediction demonstrate remarkable within-dataset performance in skeleton-based action recognition. However, we show that, unlike contrastive learning approaches, they do not produce well-separated clusters. Additionally, these methods struggle with generalization in few-shot settings. To address these issues, we propose Self-supervised Tuning for 3D Action Recognition in Skeleton sequences (STARS). Specifically, STARS first uses a masked prediction stage using an encoder-decoder architecture. It then employs nearest-neighbor contrastive learning to partially tune the weights of the encoder, enhancing the formation of semantic clusters for different actions. By tuning the encoder for a few epochs, and without using hand-crafted data augmentations, STARS achieves state-of-the-art self-supervised results in various benchmarks, including NTU-60, NTU-120, and PKU-MMD. In addition, STARS exhibits significantly better results than masked prediction models in few-shot settings, where the model has not seen the actions throughout pretraining. Project page: https://soroushmehraban.github.io/stars/

Related papers

• Skeleton2vec: A Self-supervised Learning Framework with Contextualized Target Representations for Skeleton Sequence [56.092059713922744]
  We show that using high-level contextualized features as prediction targets can achieve superior performance. Specifically, we propose Skeleton2vec, a simple and efficient self-supervised 3D action representation learning framework. Our proposed Skeleton2vec outperforms previous methods and achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2024-01-01T12:08:35Z)
• Exploring Self-supervised Skeleton-based Action Recognition in Occluded Environments [40.322770236718775]
  We propose IosPSTL, a simple and effective self-supervised learning framework designed to handle occlusions. IosPSTL combines a cluster-agnostic KNN imputer with an Occluded Partial Spatio-Temporal Learning (OPSTL) strategy. OPSTL module incorporates Adaptive Spatial Masking (ASM) to make better use of intact, high-quality skeleton sequences during training.
  arXiv  Detail & Related papers  (2023-09-21T12:51:11Z)
• SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training [110.55093254677638]
  We propose an efficient skeleton sequence learning framework, named Skeleton Sequence Learning (SSL) In this paper, we build an asymmetric graph-based encoder-decoder pre-training architecture named SkeletonMAE. Our SSL generalizes well across different datasets and outperforms the state-of-the-art self-supervised skeleton-based action recognition methods.
  arXiv  Detail & Related papers  (2023-07-17T13:33:11Z)
• Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorization [75.0912240667375]
  3D Skeleton-based human action recognition has attracted increasing attention in recent years. Most of the existing work focuses on supervised learning which requires a large number of labeled action sequences. In this paper, we address self-supervised 3D action representation learning for skeleton-based action recognition.
  arXiv  Detail & Related papers  (2023-04-18T08:03:26Z)
• SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition [13.283178393519234]
  Self-supervised skeleton-based action recognition has attracted more attention. With utilizing the unlabeled data, more generalizable features can be learned to alleviate the overfitting problem. We propose a spatial-temporal masked autoencoder framework for self-supervised 3D skeleton-based action recognition.
  arXiv  Detail & Related papers  (2022-09-01T20:54:27Z)
• 3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Na\"ive [28.720272938306692]
  We propose a Few-shot Learning pipeline for 3D skeleton-based action recognition by Joint tEmporal and cAmera viewpoiNt alIgnmEnt.
  arXiv  Detail & Related papers  (2021-12-23T16:09:23Z)
• Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning [65.88887113157627]
  Skeleton-based human action recognition has attracted increasing attention in recent years. We design a novel skeleton cloud colorization technique that is capable of learning skeleton representations from unlabeled skeleton sequence data. We show that the proposed method outperforms existing unsupervised and semi-supervised 3D action recognition methods by large margins.
  arXiv  Detail & Related papers  (2021-08-04T10:55:39Z)
• A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-Identification [65.18004601366066]
  Person re-identification (Re-ID) via gait features within 3D skeleton sequences is a newly-emerging topic with several advantages. This paper proposes a self-supervised gait encoding approach that can leverage unlabeled skeleton data to learn gait representations for person Re-ID.
  arXiv  Detail & Related papers  (2020-09-05T16:06:04Z)
• Action Localization through Continual Predictive Learning [14.582013761620738]
  We present a new approach based on continual learning that uses feature-level predictions for self-supervision. We use a stack of LSTMs coupled with CNN encoder, along with novel attention mechanisms, to model the events in the video and use this model to predict high-level features for the future frames. This self-supervised framework is not complicated as other approaches but is very effective in learning robust visual representations for both labeling and localization.
  arXiv  Detail & Related papers  (2020-03-26T23:32:43Z)
• Document Ranking with a Pretrained Sequence-to-Sequence Model [56.44269917346376]
  We show how a sequence-to-sequence model can be trained to generate relevance labels as "target words" Our approach significantly outperforms an encoder-only model in a data-poor regime.
  arXiv  Detail & Related papers  (2020-03-14T22:29:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.