{"ID":2827553,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.16504","arxiv_id":"2512.16504","title":"Skeleton-Snippet Contrastive Learning with Multiscale Feature Fusion for Action Localization","abstract":"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 skeleton-based temporal action localization remains challenging and underexplored. Unlike video-level {action} recognition, detecting action boundaries requires temporally sensitive features that capture subtle differences between adjacent frames where labels change. To this end, we formulate a snippet discrimination pretext task for self-supervised pretraining, which densely projects skeleton sequences into non-overlapping segments and promotes features that distinguish them across videos via contrastive learning. Additionally, we build on strong backbones of skeleton-based action recognition models by fusing intermediate features with a U-shaped module to enhance feature resolution for frame-level localization. Our approach consistently improves existing skeleton-based contrastive learning methods for action localization on BABEL across diverse subsets and evaluation protocols. We also achieve state-of-the-art transfer learning performance on PKUMMD with pretraining on NTU RGB+D and BABEL.","short_abstract":"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 skeleton-based temporal action localization remains challenging and underexplored. Unlike video-leve...","url_abs":"https://arxiv.org/abs/2512.16504","url_pdf":"https://arxiv.org/pdf/2512.16504v3","authors":"[\"Qiushuo Cheng\",\"Jingjing Liu\",\"Catherine Morgan\",\"Alan Whone\",\"Majid Mirmehdi\"]","published":"2025-12-18T13:15:52Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}