Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cheng, Qiushuo, Liu, Jingjing, Morgan, Catherine, Whone, Alan, Mirmehdi, Majid
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2512.16504
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910191307456512
author Cheng, Qiushuo
Liu, Jingjing
Morgan, Catherine
Whone, Alan
Mirmehdi, Majid
author_facet Cheng, Qiushuo
Liu, Jingjing
Morgan, Catherine
Whone, Alan
Mirmehdi, Majid
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_16504
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Skeleton-Snippet Contrastive Learning with Multiscale Feature Fusion for Action Localization
Cheng, Qiushuo
Liu, Jingjing
Morgan, Catherine
Whone, Alan
Mirmehdi, Majid
Computer Vision and Pattern Recognition
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.
title Skeleton-Snippet Contrastive Learning with Multiscale Feature Fusion for Action Localization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.16504