# Domain-Guided Masked Autoencoders for Unique Player Identification

arXiv: https://arxiv.org/abs/2403.11328 · HTML: https://mlsanity.com/paper/2403.11328/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 35 references that are in the map.
- First posted on arXiv 17 Mar 2024.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video](https://mlsanity.com/paper/2201.04127/) (2022)
- [GauHuman: Articulated Gaussian Splatting from Monocular Human Videos](https://mlsanity.com/paper/2312.02973/) (2023)
- [What to Hide from Your Students: Attention-Guided Masked Image Modeling](https://mlsanity.com/paper/2203.12719/) (2022)
- [AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders](https://mlsanity.com/paper/2211.09120/) (2022)
- [Player Tracking and Identification in Ice Hockey](https://mlsanity.com/paper/2110.03090/) (2021)
- [Improving Masked Autoencoders by Learning Where to Mask](https://mlsanity.com/paper/2303.06583/) (2023)
- [Multi-task learning for jersey number recognition in Ice Hockey](https://mlsanity.com/paper/2108.07848/) (2021)
- [Ice hockey player identification via transformers and weakly supervised learning](https://mlsanity.com/paper/2111.11535/) (2021)
- [Jersey Number Recognition using Keyframe Identification from Low-Resolution Broadcast Videos](https://mlsanity.com/paper/2309.06285/) (2023)
- [Player Identification in Hockey Broadcast Videos](https://mlsanity.com/paper/2009.02429/) (2020)
- [Mitigating Motion Blur for Robust 3D Baseball Player Pose Modeling for Pitch Analysis](https://mlsanity.com/paper/2309.01010/) (2023)
- [Knock, knock. Who's there? -- Identifying football player jersey numbers with synthetic data](https://mlsanity.com/paper/2203.00734/) (2022)

## Built on by (most cited first, 2 of 2)

- [PitcherNet: Powering the Moneyball Evolution in Baseball Video Analytics](https://mlsanity.com/paper/2405.07407/) (2024)
- [Ice Hockey Puck Localization Using Contextual Cues](https://mlsanity.com/paper/2506.04365/) (2025)

## Abstract (arXiv)

Unique player identification is a fundamental module in vision-driven sports analytics. Identifying players from broadcast videos can aid with various downstream tasks such as player assessment, in-game analysis, and broadcast production. However, automatic detection of jersey numbers using deep features is challenging primarily due to: a) motion blur, b) low resolution video feed, and c) occlusions. With their recent success in various vision tasks, masked autoencoders (MAEs) have emerged as a superior alternative to conventional feature extractors. However, most MAEs simply zero-out image patches either randomly or focus on where to mask rather than how to mask. Motivated by human vision, we devise a novel domain-guided masking policy for MAEs termed d-MAE to facilitate robust feature extraction in the presence of motion blur for player identification. We further introduce a new spatio-temporal network leveraging our novel d-MAE for unique player identification. We conduct experiments on three large-scale sports datasets, including a curated baseball dataset, the SoccerNet dataset, and an in-house ice hockey dataset. We preprocess the datasets using an upgraded keyframe identification (KfID) module by focusing on frames containing jersey numbers. Additionally, we propose a keyframe-fusion technique to augment keyframes, preserving spatial and temporal context. Our spatio-temporal network showcases significant improvements, surpassing the current state-of-the-art by 8.58%, 4.29%, and 1.20% in the test set accuracies, respectively. Rigorous ablations highlight the effectiveness of our domain-guided masking approach and the refined KfID module, resulting in performance enhancements of 1.48% and 1.84% respectively, compared to original architectures.