Scholarlink

<p>To address the limitations in data augmentation and neglect of joint dependencies in self-supervised human action recognition, this paper proposes a hybrid framework that integrates topology-masked motion modeling with contrastive learning. The proposed motion topology-masking technique jointly encodes skeletal topology and motion dynamics, preventing the model from over-focusing on temporally salient regions of prominent motions. We employ a multi-stage hybrid augmentation strategy, combining conventional and extreme augmentation methods to generate diverse, enriched positive pairs for contrastive learning. Additionally, we introduce a trajectory-guided feature dropping module, which selectively discards critical features based on trajectory attention maps, preventing the model from avoiding excessive focus on local joint trajectories. This approach effectively leverages large-scale unlabeled skeleton data through self-supervised learning, significantly reducing reliance on costly annotated datasets. Extensive experiments on NTU-60, NTU-120, and PKU-MMD demonstrate that the proposed model achieves superior performance in both occluded scenarios under complex environments and low-supervision conditions. It effectively mitigates visual interference and annotation scarcity while substantially improving action recognition accuracy.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Skeleton motion topology-masked prediction and contrastive learning for self-supervised human action recognition

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月10日

查看全文
  • Yan Hui,
  • Fengyu Li,
  • Xiuhua Hu,
  • Xin Guo,
  • Chao Shen

摘要

To address the limitations in data augmentation and neglect of joint dependencies in self-supervised human action recognition, this paper proposes a hybrid framework that integrates topology-masked motion modeling with contrastive learning. The proposed motion topology-masking technique jointly encodes skeletal topology and motion dynamics, preventing the model from over-focusing on temporally salient regions of prominent motions. We employ a multi-stage hybrid augmentation strategy, combining conventional and extreme augmentation methods to generate diverse, enriched positive pairs for contrastive learning. Additionally, we introduce a trajectory-guided feature dropping module, which selectively discards critical features based on trajectory attention maps, preventing the model from avoiding excessive focus on local joint trajectories. This approach effectively leverages large-scale unlabeled skeleton data through self-supervised learning, significantly reducing reliance on costly annotated datasets. Extensive experiments on NTU-60, NTU-120, and PKU-MMD demonstrate that the proposed model achieves superior performance in both occluded scenarios under complex environments and low-supervision conditions. It effectively mitigates visual interference and annotation scarcity while substantially improving action recognition accuracy.