VIFSS: View-Invariant and Figure Skating-Specific Pose Representation Learning for Temporal Action Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tanaka, Ryota, Suzuki, Tomohiro, Fujii, Keisuke
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908489818832896
author Tanaka, Ryota
Suzuki, Tomohiro
Fujii, Keisuke
author_facet Tanaka, Ryota
Suzuki, Tomohiro
Fujii, Keisuke
contents Understanding human actions from videos plays a critical role across various domains, including sports analytics. In figure skating, accurately recognizing the type and timing of jumps a skater performs is essential for objective performance evaluation. However, this task typically requires expert-level knowledge due to the fine-grained and complex nature of jump procedures. While recent approaches have attempted to automate this task using Temporal Action Segmentation (TAS), there are two major limitations to TAS for figure skating: the annotated data is insufficient, and existing methods do not account for the inherent three-dimensional aspects and procedural structure of jump actions. In this work, we propose a new TAS framework for figure skating jumps that explicitly incorporates both the three-dimensional nature and the semantic procedure of jump movements. First, we propose a novel View-Invariant, Figure Skating-Specific pose representation learning approach (VIFSS) that combines contrastive learning as pre-training and action classification as fine-tuning. For view-invariant contrastive pre-training, we construct FS-Jump3D, the first publicly available 3D pose dataset specialized for figure skating jumps. Second, we introduce a fine-grained annotation scheme that marks the ``entry (preparation)'' and ``landing'' phases, enabling TAS models to learn the procedural structure of jumps. Extensive experiments demonstrate the effectiveness of our framework. Our method achieves over 92% F1@50 on element-level TAS, which requires recognizing both jump types and rotation levels. Furthermore, we show that view-invariant contrastive pre-training is particularly effective when fine-tuning data is limited, highlighting the practicality of our approach in real-world scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2508_10281
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VIFSS: View-Invariant and Figure Skating-Specific Pose Representation Learning for Temporal Action Segmentation
Tanaka, Ryota
Suzuki, Tomohiro
Fujii, Keisuke
Computer Vision and Pattern Recognition
Understanding human actions from videos plays a critical role across various domains, including sports analytics. In figure skating, accurately recognizing the type and timing of jumps a skater performs is essential for objective performance evaluation. However, this task typically requires expert-level knowledge due to the fine-grained and complex nature of jump procedures. While recent approaches have attempted to automate this task using Temporal Action Segmentation (TAS), there are two major limitations to TAS for figure skating: the annotated data is insufficient, and existing methods do not account for the inherent three-dimensional aspects and procedural structure of jump actions. In this work, we propose a new TAS framework for figure skating jumps that explicitly incorporates both the three-dimensional nature and the semantic procedure of jump movements. First, we propose a novel View-Invariant, Figure Skating-Specific pose representation learning approach (VIFSS) that combines contrastive learning as pre-training and action classification as fine-tuning. For view-invariant contrastive pre-training, we construct FS-Jump3D, the first publicly available 3D pose dataset specialized for figure skating jumps. Second, we introduce a fine-grained annotation scheme that marks the ``entry (preparation)'' and ``landing'' phases, enabling TAS models to learn the procedural structure of jumps. Extensive experiments demonstrate the effectiveness of our framework. Our method achieves over 92% F1@50 on element-level TAS, which requires recognizing both jump types and rotation levels. Furthermore, we show that view-invariant contrastive pre-training is particularly effective when fine-tuning data is limited, highlighting the practicality of our approach in real-world scenarios.
title VIFSS: View-Invariant and Figure Skating-Specific Pose Representation Learning for Temporal Action Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.10281