paper-with-me

Papers

Skeleton-Contrastive 3D Action Representation Learning

2021-08-08 · Fida Mohammad Thoker, Hazel Doughty, Cees G. M. Snoek

This paper strives for self-supervised learning of a feature space suitable for skeleton-based action recognition. Our proposal is built upon learning invariances to input skeleton representations and various skeleton augmentations via a noise contrastive estimation. In particular, we propose inter-skeleton contrastive learning, which learns from multiple different input skeleton representations in a cross-contrastive manner. In addition, we contribute several skeleton-specific spatial and temporal augmentations which further encourage the model to learn the spatio-temporal dynamics of skeleton data. By learning similarities between different skeleton representations as well as augmented views of the same sequence, the network is encouraged to learn higher-level semantics of the skeleton data than when only using the augmented views. Our approach achieves state-of-the-art performance for self-supervised learning from skeleton data on the challenging PKU and NTU datasets with multiple downstream tasks, including action recognition, action retrieval and semi-supervised learning. Code is available at https://github.com/fmthoker/skeleton-contrast.

📄 PDF Abstract BibTeX arXiv:2108.03656

Code (1)

fmthoker/skeleton-contrast 공식 구현 pytorch

Tasks

Action RecognitionContrastive LearningFew-Shot Skeleton-Based Action RecognitionRepresentation LearningRetrievalSelf-Supervised LearningSelf-supervised Skeleton-based Action RecognitionSkeleton Based Action Recognition

Similar Papers 제목 키워드 기반

Part Aware Contrastive Learning for Self-Supervised Action Recognition

2023-05-01 · Yilei Hua, Wenhan Wu, Ce Zheng, Aidong Lu 외

In recent years, remarkable results have been achieved in self-supervised action recognition using skeleton sequences with contrastive learning. It has been observed that the semantic distinction of human action features…

Action RecognitionContrastive LearningData AugmentationRepresentation Learning+3

MS-CLR: Multi-Skeleton Contrastive Learning for Human Action Recognition

2025-08-20 · Mert Kiray, Alvaro Ritter, Nassir Navab, Benjamin Busam arxiv

Contrastive learning has gained significant attention in skeleton-based action recognition for its ability to learn robust representations from unlabeled data. However, existing methods rely on a single skeleton conventi…

Contrastive LearningAction Recognition

Skeleton-Snippet Contrastive Learning with Multiscale Feature Fusion for Action Localization

2025-12-18 · Qiushuo Cheng, Jingjing Liu, Catherine Morgan, Alan Whone 외 arxiv

The self-supervised pretraining paradigm has achieved great success in learning 3D action representations for skeleton-based action recognition using contrastive learning. However, learning effective representations for …

Temporal Action LocalizationContrastive LearningAction RecognitionTransfer Learning

Contrastive Learning from Spatio-Temporal Mixed Skeleton Sequences for Self-Supervised Skeleton-Based Action Recognition

2022-07-07 · Zhan Chen, Hong Liu, Tianyu Guo, Zhengyan Chen 외

Self-supervised skeleton-based action recognition with contrastive learning has attracted much attention. Recent literature shows that data augmentation and large sets of contrastive pairs are crucial in learning such re…

Action RecognitionContrastive LearningData AugmentationSelf-supervised Skeleton-based Action Recognition+1

Variational Contrastive Learning for Skeleton-based Action Recognition

2026-01-12 · Dang Dinh Nguyen, Decky Aspandi Latif, Titus Zaharia arxiv

In recent years, self-supervised representation learning for skeleton-based action recognition has advanced with the development of contrastive learning methods. However, most of contrastive paradigms are inherently disc…

Self-Supervised LearningRepresentation LearningContrastive LearningAction Recognition