mlsanityData to 7 Oct 2026

SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries

arXiv 2304.04565 ↗First posted 10 Apr 2023cs.CVcited by 57

Not on the map. Why?

Abstract (arXiv)

Soccer is more than just a game - it is a passion that transcends borders and unites people worldwide. From the roar of the crowds to the excitement of the commentators, every moment of a soccer match is a thrill. Yet, with so many games happening simultaneously, fans cannot watch them all live. Notifications for main actions can help, but lack the engagement of live commentary, leaving fans feeling disconnected. To fulfill this need, we propose in this paper a novel task of dense video captioning focusing on the generation of textual commentaries anchored with single timestamps. To support this task, we additionally present a challenging dataset consisting of almost 37k timestamped commentaries across 715.9 hours of soccer broadcast videos. Additionally, we propose a first benchmark and baseline for this task, highlighting the difficulty of temporally anchoring commentaries yet showing the capacity to generate meaningful commentaries. By providing broadcasters with a tool to summarize the content of their video with the same level of engagement as a live game, our method could help satisfy the needs of the numerous fans who follow their team but cannot necessarily watch the live game. We believe our method has the potential to enhance the accessibility and understanding of soccer content for a wider audience, bringing the excitement of the game to more people.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). Builds on 57 of its 89 references that are in the map. First posted on arXiv 10 Apr 2023.

Builds on

57 of 89 references.

References · 57

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  5. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  6. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  7. 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,027
  8. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
  9. 2021Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrievalcited by 1,175
  10. 2019HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clipscited by 946
  11. 2017Dense-Captioning Events in Videoscited by 789
  12. 2017Localizing Moments in Video with Natural Languagecited by 660
38 more
  1. 2017Towards Automatic Learning of Procedures from Web Instructional Videoscited by 616
  2. 2016Hollywood in Homes: Crowdsourcing Data Collection for Activity Understandingcited by 535
  3. 2020Rescaling Egocentric Visioncited by 529
  4. 2019End-to-End Learning of Visual Representations from Uncurated Instructional Videoscited by 506
  5. 2016YouTube-8M: A Large-Scale Video Classification Benchmarkcited by 324
  6. 2015MovieQA: Understanding Stories in Movies through Question-Answeringcited by 304
  7. 2023Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioningcited by 263
  8. 2020Just Ask: Learning to Answer Questions from Millions of Narrated Videoscited by 248
  9. 2015A Dataset for Movie Descriptioncited by 195
  10. 2015DenseCap: Fully Convolutional Localization Networks for Dense Captioningcited by 176
  11. 2018SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videoscited by 148
  12. 2021End-to-End Dense Video Captioning with Parallel Decodingcited by 133
  13. 2020SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videoscited by 129
  14. 2022End-to-end Generative Pretraining for Multimodal Video Captioningcited by 115
  15. 2020Multi-modal Dense Video Captioningcited by 113
  16. 2021MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptionscited by 107
  17. 2022SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videoscited by 80
  18. 2020Multimodal Pretraining for Dense Video Captioningcited by 79
  19. 2020A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformercited by 75
  20. 2022Body Part-Based Representation Learning for Occluded Person Re-Identificationcited by 63
  21. 2019A Context-Aware Loss Function for Action Spotting in Soccer Videoscited by 56
  22. 2014Coherent Multi-Sentence Video Description with Variable Level of Detailcited by 45
  23. 2021Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of their Representations for Action Spottingcited by 43
  24. 2022Spotting Temporally Precise, Fine-Grained Events in Videocited by 40
  25. 2021EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matchingcited by 36
  26. 2022DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotationscited by 35
  27. 2021Temporally-Aware Feature Pooling for Action Spotting in Soccer Broadcastscited by 30
  28. 2022SoccerNet 2022 Challenges Resultscited by 28
  29. 2023GOAL: A Challenging Knowledge-grounded Video Captioning Benchmark for Real-time Soccer Commentary Generationcited by 28
  30. 2020Game Plan: What AI can do for Football, and What Football can do for AIcited by 27
  31. 2021Feature Combination Meets Attention: Baidu Soccer Embeddings and Transformer based Temporal Detectioncited by 27
  32. 2022Temporally Precise Action Spotting in Soccer Videos Using Dense Detection Anchorscited by 27
  33. 2022A Survey on Video Action Recognition in Sports: Datasets, Methods and Applicationscited by 27
  34. 2022Semi-Supervised Training to Improve Player and Ball Detection in Soccercited by 25
  35. 2022MonoTrack: Shuttle trajectory reconstruction from monocular badminton videocited by 24
  36. 2020Using Player's Body-Orientation to Model Pass Feasibility in Soccercited by 20
  37. 2022Ball 3D Localization From A Single Calibrated Imagecited by 17
  38. 2022Efficient tracking of team sport players with few game-specific annotationscited by 17

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 14; 2025: 16; 2026: 25.

57 papers.

Sort:

By area:

  1. 2024MatchTime: Towards Automatic Soccer Game Commentary Generationcited by 37
  2. 2024SoccerNet Game State Reconstruction: End-to-End Athlete Tracking and Identification on a Minimapcited by 34
  3. 2024X-VARS: Introducing Explainability in Football Refereeing with Multi-Modal Large Language Modelcited by 22
  4. 2024Towards Universal Soccer Video Understandingcited by 21
  5. 2023SoccerNet 2023 Challenges Resultscited by 20
  6. 2025TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generationcited by 13
  7. 2024Multi-task Learning for Joint Re-identification, Team Affiliation, and Role Classification for Sports Visual Trackingcited by 12
  8. 2024SoccerNet-Echoes: A Soccer Game Audio Commentary Datasetcited by 12
  9. 2023A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decisioncited by 11
  10. 2025SoccerMaster: A Vision Foundation Model for Soccer Understandingcited by 10
  11. 2024Towards AI-Powered Video Assistant Referee System (VARS) for Association Footballcited by 8
  12. 2024SoccerNet 2024 Challenges Resultscited by 8
38 more
  1. 2025SoccerChat: Integrating Multimodal Data for Enhanced Soccer Game Understandingcited by 8
  2. 2026Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Modelcited by 8
  3. 2024Foul prediction with estimated poses from soccer broadcast videocited by 7
  4. 2024Deep learning for action spotting in association football videoscited by 7
  5. 2025F3Set: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videoscited by 7
  6. 2025LiveCC: Learning Video LLM with Streaming Speech Transcription at Scalecited by 7
  7. 2025Domain Adaptation of VLM for Soccer Video Understandingcited by 7
  8. 2025Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioningcited by 7
  9. 2025Sali4Vid: Saliency-Aware Video Reweighting and Adaptive Caption Retrieval for Dense Video Captioningcited by 4
  10. 2025From Multimodal Perception to Strategic Reasoning: A Survey on AI-Generated Game Commentarycited by 3
  11. 2025SV3.3B: A Sports Video Understanding Model for Action Recognitioncited by 3
  12. 2026Cut to the Chase: Training-free Multimodal Summarization via Chain-of-Eventscited by 3
  13. 2024Knowledge Guided Entity-aware Video Captioning and A Basketball Benchmarkcited by 2
  14. 2024OSL-ActionSpotting: A Unified Library for Action Spotting in Sports Videoscited by 2
  15. 2025Shot2Tactic-Caption: Multi-Scale Captioning of Badminton Videos for Tactical Understandingcited by 2
  16. 2025X-Ego: Acquiring Team-Level Tactical Situational Awareness via Cross-Egocentric Contrastive Video Representation Learningcited by 2
  17. 2026Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sportscited by 2
  18. 2026GenTac: Generative Modeling and Forecasting of Soccer Tacticscited by 2
  19. 2024Investigating Event-Based Cameras for Video Frame Interpolation in Sportscited by 1
  20. 2025Do We Need Large VLMs for Spotting Soccer Actions?cited by 1
  21. 2025MCAD: Multimodal Context-Aware Audio Description Generation For Soccercited by 1
  22. 2026Follow the Saliency: Supervised Saliency for Retrieval-augmented Dense Video Captioningcited by 1
  23. 2026TennisExpert: Towards Expert-Level Analytical Sports Video Understandingcited by 1
  24. 2026Towards Automatic Soccer Commentary Generation with Knowledge-Enhanced Visual Reasoningcited by 1
  25. 2026Towards Athlete Fatigue Assessment from Association Football Videoscited by 1
  26. 2026RefereeBench: Are Video MLLMs Ready to be Multi-Sport Refereescited by 1
  27. 2026SoccerNet 2026 Challenges Resultscited by 1
  28. 2024PLayerTV: Advanced Player Tracking and Identification for Automatic Soccer Highlight Clipscited by 0
  29. 2025Commentary Generation for Soccer Highlightscited by 0
  30. 2025TrajSV: A Trajectory-based Model for Sports Video Representations and Applicationscited by 0
  31. 2026Generalizing Sports Feedback Generation by Watching Competitions and Reading Books: A Rock Climbing Case Studycited by 0
  32. 2026BFMD: A Full-Match Badminton Dense Dataset for Dense Shot Captioningcited by 0
  33. 2026BoxComm: Benchmarking Category-Aware Commentary Generation and Narration Rhythm in Boxingcited by 0
  34. 2026SoccerRef-Agents: Multi-Agent System for Automated Soccer Refereeingcited by 0
  35. 2026SoccerLens: Grounded Soccer Video Understanding Beyond Accuracycited by 0
  36. 2026MSUE: Multi-Modal Soccer Understanding Expertcited by 0
  37. 2026TreeSoc: Tree-Structured Dynamic Reasoning and Tool Synergy for Soccer Video Understandingcited by 0
  38. 2026VIABench: A Comprehensive Video Benchmark Collected from Blind Individuals for Visual Impairment Assistancecited by 0

50 most cited of 57 All 57 (JSON)