mlsanityData to 13 Oct 2026

Going for GOAL: A Resource for Grounded Football Commentaries

arXiv 2211.04534 ↗First posted 8 Nov 2022cs.CV cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

Recent video+language datasets cover domains where the interaction is highly structured, such as instructional videos, or where the interaction is scripted, such as TV shows. Both of these properties can lead to spurious cues to be exploited by models rather than learning to ground language. In this paper, we present GrOunded footbAlL commentaries (GOAL), a novel dataset of football (or `soccer') highlights videos with transcribed live commentaries in English. As the course of a game is unpredictable, so are commentaries, which makes them a unique resource to investigate dynamic language grounding. We also provide state-of-the-art baselines for the following tasks: frame reordering, moment retrieval, live commentary retrieval and play-by-play live commentary generation. Results show that SOTA models perform reasonably well in most tasks. We discuss the implications of these results and suggest new tasks for which GOAL can be used. Our codebase is available at: https://gitlab.com/grounded-sport-convai/goal-baselines.

Key facts. Cited by 7 papers in the map (data through 13 Oct 2026). Builds on 48 of its 73 references that are in the map. First posted on arXiv 8 Nov 2022.

Builds on

48 of 73 references.

References · 48

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,322
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,884
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,480
  5. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,024
  6. 2019The Curious Case of Neural Text Degenerationcited by 2,893
  7. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  8. 2018Hierarchical Neural Story Generationcited by 1,186
  9. 2017Dense-Captioning Events in Videoscited by 790
  10. 2017Localizing Moments in Video with Natural Languagecited by 661
  11. 2019Multimodal Transformer for Unaligned Multimodal Language Sequencescited by 639
  12. 2017Towards Automatic Learning of Procedures from Web Instructional Videoscited by 616
36 more
  1. 2018From Recognition to Cognition: Visual Commonsense Reasoningcited by 553
  2. 2016Visual Dialogcited by 377
  3. 2020HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-trainingcited by 362
  4. 2018AllenNLP: A Deep Semantic Natural Language Processing Platformcited by 347
  5. 2020UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generationcited by 259
  6. 2017The E2E Dataset: New Challenges For End-to-End Generationcited by 253
  7. 2017Why We Need New Evaluation Metrics for NLGcited by 232
  8. 2017Challenges in Data-to-Document Generationcited by 226
  9. 2016Incorporating Copying Mechanism in Sequence-to-Sequence Learningcited by 217
  10. 2020TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrievalcited by 215
  11. 2018End-to-End Dense Video Captioning with Masked Transformercited by 214
  12. 2019Leveraging Pre-trained Checkpoints for Sequence Generation Taskscited by 182
  13. 2016Movie Descriptioncited by 180
  14. 2020Adversarial Filters of Dataset Biasescited by 160
  15. 2019TVQA+: Spatio-Temporal Grounding for Video Question Answeringcited by 153
  16. 2019What makes a good conversation? How controllable attributes affect human judgmentscited by 140
  17. 2018How2: A Large-scale Dataset for Multimodal Language Understandingcited by 138
  18. 2020SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videoscited by 129
  19. 2019Audio-Visual Scene-Aware Dialogcited by 122
  20. 2021VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluationcited by 95
  21. 2020Multimodal Pretraining for Dense Video Captioningcited by 79
  22. 2018Image Chat: Engaging Grounded Conversationscited by 76
  23. 2019A Context-Aware Loss Function for Action Spotting in Soccer Videoscited by 56
  24. 2021ACAV100M: Automatic Curation of Large-Scale Datasets for Audio-Visual Video Representation Learningcited by 50
  25. 2016Re-evaluating Automatic Metrics for Image Captioningcited by 45
  26. 2019Data-to-text Generation with Entity Modelingcited by 45
  27. 2019The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agentscited by 45
  28. 2020Towards Ecologically Valid Research on Language User Interfacescited by 42
  29. 2020VIOLIN: A Large-Scale Dataset for Video-and-Language Inferencecited by 41
  30. 2020Situated and Interactive Multimodal Conversationscited by 35
  31. 2020History for Visual Dialog: Do we really need it?cited by 32
  32. 2018Shifting the Baseline: Single Modality Performance on Visual Navigation & QAcited by 30
  33. 2020GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systemscited by 29
  34. 2018Game-Based Video-Context Dialoguecited by 15
  35. 2020Listen, Look and Deliberate: Visual context-aware speech recognition using pre-trained text-video representationscited by 10
  36. 2021SOCCER: An Information-Sparse Discourse State Tracking Collection in the Sports Commentary Domaincited by 4

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2023: 3; 2024: 2; 2025: 1; 2026: 1.

7 papers.

  1. 2023SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentariescited by 57
  2. 2023GOAL: A Challenging Knowledge-grounded Video Captioning Benchmark for Real-time Soccer Commentary Generationcited by 28
  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. 2023Survey of Action Recognition, Spotting and Spatio-Temporal Localization in Soccer -- Current Trends and Research Perspectivescited by 7
  6. 2025Shot2Tactic-Caption: Multi-Scale Captioning of Badminton Videos for Tactical Understandingcited by 2
  7. 2026BFMD: A Full-Match Badminton Dense Dataset for Dense Shot Captioningcited by 0