Saved in:
Bibliographic Details
Main Authors: Tian, Haitao, Payeur, Pierre
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.05543
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915482998669312
author Tian, Haitao
Payeur, Pierre
author_facet Tian, Haitao
Payeur, Pierre
contents In this paper, a contrastive representation learning framework is proposed to enhance human action segmentation via pre-training using trimmed (single action) skeleton sequences. Unlike previous representation learning works that are tailored for action recognition and that build upon isolated sequence-wise representations, the proposed framework focuses on exploiting multi-scale representations in conjunction with cross-sequence variations. More specifically, it proposes a novel data augmentation strategy, 'Shuffle and Warp', which exploits diverse multi-action permutations. The latter effectively assists two surrogate tasks that are introduced in contrastive learning: Cross Permutation Contrasting (CPC) and Relative Order Reasoning (ROR). In optimization, CPC learns intra-class similarities by contrasting representations of the same action class across different permutations, while ROR reasons about inter-class contexts by predicting relative mapping between two permutations. Together, these tasks enable a Dual-Surrogate Contrastive Learning (DuoCLR) network to learn multi-scale feature representations optimized for action segmentation. In experiments, DuoCLR is pre-trained on a trimmed skeleton dataset and evaluated on an untrimmed dataset where it demonstrates a significant boost over state-the-art comparatives in both multi-class and multi-label action segmentation tasks. Lastly, ablation studies are conducted to evaluate the effectiveness of each component of the proposed approach.
format Preprint
id arxiv_https___arxiv_org_abs_2509_05543
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DuoCLR: Dual-Surrogate Contrastive Learning for Skeleton-based Human Action Segmentation
Tian, Haitao
Payeur, Pierre
Computer Vision and Pattern Recognition
In this paper, a contrastive representation learning framework is proposed to enhance human action segmentation via pre-training using trimmed (single action) skeleton sequences. Unlike previous representation learning works that are tailored for action recognition and that build upon isolated sequence-wise representations, the proposed framework focuses on exploiting multi-scale representations in conjunction with cross-sequence variations. More specifically, it proposes a novel data augmentation strategy, 'Shuffle and Warp', which exploits diverse multi-action permutations. The latter effectively assists two surrogate tasks that are introduced in contrastive learning: Cross Permutation Contrasting (CPC) and Relative Order Reasoning (ROR). In optimization, CPC learns intra-class similarities by contrasting representations of the same action class across different permutations, while ROR reasons about inter-class contexts by predicting relative mapping between two permutations. Together, these tasks enable a Dual-Surrogate Contrastive Learning (DuoCLR) network to learn multi-scale feature representations optimized for action segmentation. In experiments, DuoCLR is pre-trained on a trimmed skeleton dataset and evaluated on an untrimmed dataset where it demonstrates a significant boost over state-the-art comparatives in both multi-class and multi-label action segmentation tasks. Lastly, ablation studies are conducted to evaluate the effectiveness of each component of the proposed approach.
title DuoCLR: Dual-Surrogate Contrastive Learning for Skeleton-based Human Action Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.05543