# Sports Re-ID: Improving Re-Identification Of Players In Broadcast Videos Of Team Sports arXiv: https://arxiv.org/abs/2206.02373 ยท HTML: https://mlsanity.com/paper/2206.02373/ ## Key facts - Cited by 6 papers in the map (data through 14 Oct 2026). - Builds on 19 of its 34 references that are in the map. - First posted on arXiv 6 Jun 2022. ## Builds on (most cited first, 19 of 19) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014) - [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020) - [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016) - [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020) - [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017) - [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017) - [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021) - [Omni-Scale Feature Learning for Person Re-Identification](https://mlsanity.com/paper/1905.00953/) (2019) - [SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos](https://mlsanity.com/paper/2011.13367/) (2020) - [Hierarchical Clustering with Hard-batch Triplet Loss for Person Re-identification](https://mlsanity.com/paper/1910.12278/) (2019) - [Learning Generalisable Omni-Scale Representations for Person Re-Identification](https://mlsanity.com/paper/1910.06827/) (2019) - [On the Unreasonable Effectiveness of Centroids in Image Retrieval](https://mlsanity.com/paper/2104.13643/) (2021) - [Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch](https://mlsanity.com/paper/1910.10093/) (2019) - [In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillation](https://mlsanity.com/paper/1912.07863/) (2019) - [A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning](https://mlsanity.com/paper/1904.08720/) (2019) - [Centroid-based deep metric learning for speaker recognition](https://mlsanity.com/paper/1902.02375/) (2019) - [Beyond Intra-modality: A Survey of Heterogeneous Person Re-identification](https://mlsanity.com/paper/1905.10048/) (2019) - [Beyond Triplet Loss: Meta Prototypical N-tuple Loss for Person Re-identification](https://mlsanity.com/paper/2006.04991/) (2020) ## Built on by (most cited first, 6 of 6) - [SoccerNet 2022 Challenges Results](https://mlsanity.com/paper/2210.02365/) (2022) - [Transformer for Object Re-Identification: A Survey](https://mlsanity.com/paper/2401.06960/) (2024) - [A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision](https://mlsanity.com/paper/2307.03353/) (2023) - [CLIP-ReIdent: Contrastive Training for Player Re-Identification](https://mlsanity.com/paper/2303.11855/) (2023) - [Runner re-identification from single-view running video in the open-world setting](https://mlsanity.com/paper/2310.11700/) (2023) - [Multi Camera Connected Vision System with Multi View Analytics: A Comprehensive Survey](https://mlsanity.com/paper/2510.09731/) (2025) ## Abstract (arXiv) This work focuses on player re-identification in broadcast videos of team sports. Specifically, we focus on identifying the same player in images captured from different camera viewpoints during any given moment of a match. This task differs from traditional applications of person re-id in a few important ways. Firstly, players from the same team wear highly similar clothes, thereby making it harder to tell them apart. Secondly, there are only a few number of samples for each identity, which makes it harder to train a re-id system. Thirdly, the resolutions of the images are often quite low and vary a lot. This combined with heavy occlusions and fast movements of players greatly increase the challenges for re-id. In this paper, we propose a simple but effective hierarchical data sampling procedure and a centroid loss function that, when used together, increase the mean average precision (mAP) by 7 - 11.5 and the rank-1 (R1) by 8.8 - 14.9 without any change in the network or hyper-parameters used. Our data sampling procedure improves the similarity of the training and test distributions, and thereby aids in creating better estimates of the centroids of the embeddings (or feature vectors). Surprisingly, our study shows that in the presence of severely limited data, as is the case for our application, a simple centroid loss function based on euclidean distances significantly outperforms the popular triplet-centroid loss function. We show comparable improvements for both convolutional networks and vision transformers. Our approach is among the top ranked methods in the SoccerNet Re-Identification Challenge 2022 leaderboard (test-split) with a mAP of 86.0 and a R1 of 81.5. On the sequestered challenge split, we achieve an mAP of 84.9 and a R1 of 80.1. Research on re-id for sports-related applications is very limited and our work presents one of the first discussions in the literature on this.