# Biomechanical-phase based Temporal Segmentation in Sports Videos: a Demonstration on Javelin-Throw

arXiv: https://arxiv.org/abs/2509.24606 · HTML: https://mlsanity.com/paper/2509.24606/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Builds on (most cited first, 26 of 26)

- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [Video Action Transformer Network](https://mlsanity.com/paper/1812.02707/) (2018)
- [Optimal Transport for structured data with application on graphs](https://mlsanity.com/paper/1805.09114/) (2018)
- [Fused Gromov-Wasserstein distance for structured objects: theoretical foundations and mathematical properties](https://mlsanity.com/paper/1811.02834/) (2018)
- [Temporal Action Segmentation: An Analysis of Modern Techniques](https://mlsanity.com/paper/2210.10352/) (2022)
- [Unsupervised learning of action classes with continuous temporal embedding](https://mlsanity.com/paper/1904.04189/) (2019)
- [Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation](https://mlsanity.com/paper/2003.02824/) (2020)
- [Background Suppression Network for Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/1911.09963/) (2019)
- [mm-Pose: Real-Time Human Skeletal Posture Estimation using mmWave Radars and CNNs](https://mlsanity.com/paper/1911.09592/) (2019)
- [Weakly-Supervised Action Localization by Generative Attention Modeling](https://mlsanity.com/paper/2003.12424/) (2020)
- [The Unbalanced Gromov Wasserstein Distance: Conic Formulation and Relaxation](https://mlsanity.com/paper/2009.04266/) (2020)
- [Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering](https://mlsanity.com/paper/2105.13353/) (2021)
- [Joint Visual-Temporal Embedding for Unsupervised Learning of Actions in Untrimmed Sequences](https://mlsanity.com/paper/2001.11122/) (2020)
- [Adversarial Background-Aware Loss for Weakly-supervised Temporal Activity Localization](https://mlsanity.com/paper/2007.06643/) (2020)
- [Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation](https://mlsanity.com/paper/2404.01518/) (2024)
- [Scaling Algorithms for Unbalanced Transport Problems](https://mlsanity.com/paper/1607.05816/) (2016)
- [Action Shuffle Alternating Learning for Unsupervised Action Segmentation](https://mlsanity.com/paper/2104.02116/) (2021)
- [Unsupervised Learning from Video with Deep Neural Embeddings](https://mlsanity.com/paper/1905.11954/) (2019)
- [Action Sensitivity Learning for Temporal Action Localization](https://mlsanity.com/paper/2305.15701/) (2023)
- [Unsupervised Discriminative Embedding for Sub-Action Learning in Complex Activities](https://mlsanity.com/paper/2105.00067/) (2021)
- [Aligning individual brains with Fused Unbalanced Gromov-Wasserstein](https://mlsanity.com/paper/2206.09398/) (2022)
- [Permutation-Aware Action Segmentation via Unsupervised Frame-to-Segment Alignment](https://mlsanity.com/paper/2305.19478/) (2023)
- [LAC: Latent Action Composition for Skeleton-based Action Segmentation](https://mlsanity.com/paper/2308.14500/) (2023)
- [Efficient Approximation of Gromov-Wasserstein Distance Using Importance Sparsification](https://mlsanity.com/paper/2205.13573/) (2022)
- [Action Segmentation Using 2D Skeleton Heatmaps and Multi-Modality Fusion](https://mlsanity.com/paper/2309.06462/) (2023)

## Built on by (most cited first, 1 of 1)

- [Throwing4: Phase-Aware Pose Modeling for Throw-Distance Prediction in Elite Athletics](https://mlsanity.com/paper/2610.16383/) (2026)

## Abstract (arXiv)

Precise analysis of athletic motion is central to sports analytics, particularly in disciplines where nuanced biomechanical phases directly impact performance outcomes. Traditional analytics techniques rely on manual annotation or laboratory-based instrumentation, which are time-consuming, costly, and lack scalability. Automatic extraction of relevant kinetic variables requires a robust and contextually appropriate temporal segmentation. Considering the specific case of elite javelin-throw, we present a novel unsupervised framework for such a contextually aware segmentation, which applies the structured optimal transport (SOT) concept to augment the well-known Attention-based Spatio-Temporal Graph Convolutional Network (ASTGCN). This enables the identification of motion phase transitions without requiring expensive manual labeling. Extensive experiments demonstrate that our approach outperforms state-of-the-art unsupervised methods, achieving 71.02% mean average precision (mAP) and 74.61% F1-score on test data, substantially higher than competing baselines. We also release a new dataset of 211 manually annotated professional javelin-throw videos with frame-level annotations, covering key biomechanical phases: approach steps, drive, throw, and recovery.