# ASTRA: An Action Spotting TRAnsformer for Soccer Videos

arXiv: https://arxiv.org/abs/2404.01891 · HTML: https://mlsanity.com/paper/2404.01891/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 46 references that are in the map.
- First posted on arXiv 2 Apr 2024.

## Builds on (most cited first, 30 of 31)

- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [YouTube-8M: A Large-Scale Video Classification Benchmark](https://mlsanity.com/paper/1609.08675/) (2016)
- [Temporal Relational Reasoning in Videos](https://mlsanity.com/paper/1711.08496/) (2017)
- [FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding](https://mlsanity.com/paper/2004.06704/) (2020)
- [EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition](https://mlsanity.com/paper/1908.08498/) (2019)
- [Learning Salient Boundary Feature for Anchor-free Temporal Action Localization](https://mlsanity.com/paper/2103.13137/) (2021)
- [End-to-end Temporal Action Detection with Transformer](https://mlsanity.com/paper/2106.10271/) (2021)
- [SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos](https://mlsanity.com/paper/2011.13367/) (2020)
- [Single Shot Temporal Action Detection](https://mlsanity.com/paper/1710.06236/) (2017)
- [Temporal Context Aggregation Network for Temporal Action Proposal Refinement](https://mlsanity.com/paper/2103.13141/) (2021)
- [FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment](https://mlsanity.com/paper/2204.03646/) (2022)
- [Gate-Shift Networks for Video Action Recognition](https://mlsanity.com/paper/1912.00381/) (2019)
- [A Context-Aware Loss Function for Action Spotting in Soccer Videos](https://mlsanity.com/paper/1912.01326/) (2019)
- [Spotting Temporally Precise, Fine-Grained Events in Video](https://mlsanity.com/paper/2207.10213/) (2022)
- [Vid2Player: Controllable Video Sprites that Behave and Appear like Professional Tennis Players](https://mlsanity.com/paper/2008.04524/) (2020)
- [Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition](https://mlsanity.com/paper/2109.01305/) (2021)
- [Feature Combination Meets Attention: Baidu Soccer Embeddings and Transformer based Temporal Detection](https://mlsanity.com/paper/2106.14447/) (2021)
- [Temporally Precise Action Spotting in Soccer Videos Using Dense Detection Anchors](https://mlsanity.com/paper/2205.10450/) (2022)
- [Improved Soccer Action Spotting using both Audio and Video Streams](https://mlsanity.com/paper/2011.04258/) (2020)
- [A Comprehensive Review of Computer Vision in Sports: Open Issues, Future Trends and Research Directions](https://mlsanity.com/paper/2203.02281/) (2022)
- [Auto-Encoding Score Distribution Regression for Action Quality Assessment](https://mlsanity.com/paper/2111.11029/) (2021)
- [Action Spotting using Dense Detection Anchors Revisited: Submission to the SoccerNet Challenge 2022](https://mlsanity.com/paper/2206.07846/) (2022)
- [MAiVAR: Multimodal Audio-Image and Video Action Recognizer](https://mlsanity.com/paper/2209.04780/) (2022)

## Built on by (most cited first, 16 of 16)

- [T-DEED: Temporal-Discriminability Enhancer Encoder-Decoder for Precise Event Spotting in Sports Videos](https://mlsanity.com/paper/2404.05392/) (2024)
- [Action Anticipation from SoccerNet Football Video Broadcasts](https://mlsanity.com/paper/2504.12021/) (2025)
- [SoccerNet 2024 Challenges Results](https://mlsanity.com/paper/2409.10587/) (2024)
- [Deep learning for action spotting in association football videos](https://mlsanity.com/paper/2410.01304/) (2024)
- [Precise Event Spotting in Sports Videos: Solving Long-Range Dependency and Class Imbalance](https://mlsanity.com/paper/2503.00147/) (2025)
- [Deep Learning for Sports Video Event Detection: Tasks, Datasets, Methods, and Challenges](https://mlsanity.com/paper/2505.03991/) (2025)
- [AdaSpot: Spend Resolution Where It Matters for Precise Event Spotting](https://mlsanity.com/paper/2602.22073/) (2026)
- [Detecting Precise Hand Touch Moments in Egocentric Video](https://mlsanity.com/paper/2604.12343/) (2026)
- [Do We Need Large VLMs for Spotting Soccer Actions?](https://mlsanity.com/paper/2506.17144/) (2025)
- [Multi-Focus Temporal Shifting for Precise Event Spotting in Sports Videos](https://mlsanity.com/paper/2507.07381/) (2025)
- [ViTs for Action Classification in Videos: An Approach to Risky Tackle Detection in American Football Practice Videos](https://mlsanity.com/paper/2604.01318/) (2026)
- [SoccerTrack v2: A Full-Pitch Panoramic Video Dataset for Game State Reconstruction and Ball Action Spotting](https://mlsanity.com/paper/2508.01802/) (2025)
- [Efficient Spatial-Temporal Focal Adapter with SSM for Temporal Action Detection](https://mlsanity.com/paper/2604.09164/) (2026)
- [Temporal Feature Distillation for Label-Efficient Precise Event Spotting in Sports Videos](https://mlsanity.com/paper/2607.10998/) (2026)
- [Entity-Aware Sequence Transduction for Player-Centric Ball Action Spotting](https://mlsanity.com/paper/2608.01696/) (2026)
- [BMASH: Ball-Motion-Aware Soccer Header Spotting](https://mlsanity.com/paper/2609.39300/) (2026)

## Abstract (arXiv)

In this paper, we introduce ASTRA, a Transformer-based model designed for the task of Action Spotting in soccer matches. ASTRA addresses several challenges inherent in the task and dataset, including the requirement for precise action localization, the presence of a long-tail data distribution, non-visibility in certain actions, and inherent label noise. To do so, ASTRA incorporates (a) a Transformer encoder-decoder architecture to achieve the desired output temporal resolution and to produce precise predictions, (b) a balanced mixup strategy to handle the long-tail distribution of the data, (c) an uncertainty-aware displacement head to capture the label variability, and (d) input audio signal to enhance detection of non-visible actions. Results demonstrate the effectiveness of ASTRA, achieving a tight Average-mAP of 66.82 on the test set. Moreover, in the SoccerNet 2023 Action Spotting challenge, we secure the 3rd position with an Average-mAP of 70.21 on the challenge set.