mlsanityData to 14 Oct 2026

ASTRA: An Action Spotting TRAnsformer for Soccer Videos

arXiv 2404.01891 ↗First posted 2 Apr 2024cs.CVcited by 16

Not on the map. Why?

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.

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

31 of 46 references.

References · 31

  1. 2020End-to-End Object Detection with Transformerscited by 7,414
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  3. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  4. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  5. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,103
  6. 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 902
  7. 2016CNN Architectures for Large-Scale Audio Classificationcited by 704
  8. 2017Soft-NMS -- Improving Object Detection With One Line of Codecited by 382
  9. 2016YouTube-8M: A Large-Scale Video Classification Benchmarkcited by 324
  10. 2017Temporal Relational Reasoning in Videoscited by 324
  11. 2020FineGym: A Hierarchical Video Dataset for Fine-grained Action Understandingcited by 234
  12. 2019EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognitioncited by 226
19 more
  1. 2021Learning Salient Boundary Feature for Anchor-free Temporal Action Localizationcited by 156
  2. 2021End-to-end Temporal Action Detection with Transformercited by 151
  3. 2020SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videoscited by 131
  4. 2017Single Shot Temporal Action Detectioncited by 123
  5. 2021Temporal Context Aggregation Network for Temporal Action Proposal Refinementcited by 112
  6. 2022FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessmentcited by 107
  7. 2019Gate-Shift Networks for Video Action Recognitioncited by 76
  8. 2019A Context-Aware Loss Function for Action Spotting in Soccer Videoscited by 56
  9. 2022Spotting Temporally Precise, Fine-Grained Events in Videocited by 40
  10. 2020Vid2Player: Controllable Video Sprites that Behave and Appear like Professional Tennis Playerscited by 30
  11. 2021Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognitioncited by 29
  12. 2021Feature Combination Meets Attention: Baidu Soccer Embeddings and Transformer based Temporal Detectioncited by 27
  13. 2022Temporally Precise Action Spotting in Soccer Videos Using Dense Detection Anchorscited by 27
  14. 2020Improved Soccer Action Spotting using both Audio and Video Streamscited by 21
  15. 2022A Comprehensive Review of Computer Vision in Sports: Open Issues, Future Trends and Research Directionscited by 21
  16. 2021Auto-Encoding Score Distribution Regression for Action Quality Assessmentcited by 18
  17. 2022Action Spotting using Dense Detection Anchors Revisited: Submission to the SoccerNet Challenge 2022cited by 14
  18. 2022MAiVAR: Multimodal Audio-Image and Video Action Recognizercited by 3
  19. 2020Boundary Uncertainty in a Single-Stage Temporal Action Localization Networkcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 6; 2026: 7.

16 papers.

Sort:

  1. 2024T-DEED: Temporal-Discriminability Enhancer Encoder-Decoder for Precise Event Spotting in Sports Videoscited by 21
  2. 2025Action Anticipation from SoccerNet Football Video Broadcastscited by 9
  3. 2024SoccerNet 2024 Challenges Resultscited by 8
  4. 2024Deep learning for action spotting in association football videoscited by 7
  5. 2025Precise Event Spotting in Sports Videos: Solving Long-Range Dependency and Class Imbalancecited by 6
  6. 2025Deep Learning for Sports Video Event Detection: Tasks, Datasets, Methods, and Challengescited by 3
  7. 2026AdaSpot: Spend Resolution Where It Matters for Precise Event Spottingcited by 2
  8. 2026Detecting Precise Hand Touch Moments in Egocentric Videocited by 2
  9. 2025Do We Need Large VLMs for Spotting Soccer Actions?cited by 1
  10. 2025Multi-Focus Temporal Shifting for Precise Event Spotting in Sports Videoscited by 1
  11. 2026ViTs for Action Classification in Videos: An Approach to Risky Tackle Detection in American Football Practice Videoscited by 1
  12. 2025SoccerTrack v2: A Full-Pitch Panoramic Video Dataset for Game State Reconstruction and Ball Action Spottingcited by 0
4 more
  1. 2026Efficient Spatial-Temporal Focal Adapter with SSM for Temporal Action Detectioncited by 0
  2. 2026Temporal Feature Distillation for Label-Efficient Precise Event Spotting in Sports Videoscited by 0
  3. 2026Entity-Aware Sequence Transduction for Player-Centric Ball Action Spottingcited by 0
  4. 2026BMASH: Ball-Motion-Aware Soccer Header Spottingcited by 0