Towards Automatic Soccer Commentary Generation with Knowledge-Enhanced Visual Reasoning

• URL: http://arxiv.org/abs/2604.00057v1
• Date: Tue, 31 Mar 2026 02:24:32 GMT
• Title: Towards Automatic Soccer Commentary Generation with Knowledge-Enhanced Visual Reasoning
• Abstract summary: Soccer commentary plays a crucial role in enhancing the soccer game viewing experience for audiences.<n>Previous studies in automatic soccer commentary generation typically adopt an end-to-end method to generate anonymous live text commentary.<n>We propose GameSight, a two-stage model to address soccer commentary generation as a knowledge-enhanced visual reasoning task.
• Score: 18.388733074404403
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Soccer commentary plays a crucial role in enhancing the soccer game viewing experience for audiences. Previous studies in automatic soccer commentary generation typically adopt an end-to-end method to generate anonymous live text commentary. Such generated commentary is insufficient in the context of real-world live televised commentary, as it contains anonymous entities, context-dependent errors and lacks statistical insights of the game events. To bridge the gap, we propose GameSight, a two-stage model to address soccer commentary generation as a knowledge-enhanced visual reasoning task, enabling live-televised-like knowledgeable commentary with accurate reference to entities (players and teams). GameSight starts by performing visual reasoning to align anonymous entities with fine-grained visual and contextual analysis. Subsequently, the entity-aligned commentary is refined with knowledge by incorporating external historical statistics and iteratively updated internal game state information. Consequently, GameSight improves the player alignment accuracy by 18.5% on SN-Caption-test-align dataset compared to Gemini 2.5-pro. Combined with further knowledge enhancement, GameSight outperforms in segment-level accuracy and commentary quality, as well as game-level contextual relevance and structural composition. We believe that our work paves the way for a more informative and engaging human-centric experience with the AI sports application. Demo Page: https://gamesight2025.github.io/gamesight2025

Related papers

• SoccerLens: Grounded Soccer Video Understanding Beyond Accuracy [52.09081885158698]
  Vision-language models (VLMs) have recently shown strong potential in soccer video understanding.<n>Existing evaluation protocols focus on classification accuracy and do not assess visual grounding.<n>We introduce SoccerLens, a benchmark for grounded soccer video understanding.
  arXiv  Detail & Related papers  (2026-05-10T15:18:08Z)
• BoxComm: Benchmarking Category-Aware Commentary Generation and Narration Rhythm in Boxing [9.244368483134101]
  We present BoxComm, a large-scale dataset comprising 445 World Boxing Championship match videos with over 52K commentary sentences from professional broadcasts.<n>We propose a structured commentary taxonomy that categorizes each sentence into play-by-play, tactical, or contextual.<n>We introduce two novel and complementary evaluations tailored to sports commentary generation.
  arXiv  Detail & Related papers  (2026-04-06T04:56:49Z)
• Commentary Generation for Soccer Highlights [0.0]
  We extend MatchVoice to commentary generation for soccer highlights using the GOAL dataset.<n>We conduct extensive experiments to reproduce the original MatchTime results and evaluate our setup.<n>Our findings suggest the need for integrating techniques from broader video-language domains to further enhance performance.
  arXiv  Detail & Related papers  (2025-08-11T01:48:37Z)
• SoccerChat: Integrating Multimodal Data for Enhanced Soccer Game Understanding [44.04695944511487]
  SoccerChat is a conversational AI framework that integrates visual and textual data for enhanced soccer video comprehension.<n>We benchmark SoccerChat on action classification and referee decision-making tasks, demonstrating its performance in general soccer event comprehension.<n>Our findings highlight the importance of multimodal integration in advancing soccer analytics, paving the way for more interactive and explainable AI-driven sports analysis.
  arXiv  Detail & Related papers  (2025-05-22T13:01:51Z)
• MatchTime: Towards Automatic Soccer Game Commentary Generation [52.431010585268865]
  We consider constructing an automatic soccer game commentary model to improve the audiences' viewing experience. First, observing the prevalent video-text misalignment in existing datasets, we manually annotate timestamps for 49 matches. Second, we propose a multi-modal temporal alignment pipeline to automatically correct and filter the existing dataset at scale. Third, based on our curated dataset, we train an automatic commentary generation model, named MatchVoice.
  arXiv  Detail & Related papers  (2024-06-26T17:57:25Z)
• Game-MUG: Multimodal Oriented Game Situation Understanding and Commentary Generation Dataset [8.837048597513059]
  This paper introduces GAME-MUG, a new multimodal game situation understanding and audience-engaged commentary generation dataset. Our dataset is collected from 2020-2022 LOL game live streams from YouTube and Twitch, and includes multimodal esports game information, including text, audio, and time-series event logs. In addition, we also propose a new audience conversation augmented commentary dataset by covering the game situation and audience conversation understanding.
  arXiv  Detail & Related papers  (2024-04-30T00:39:26Z)
• SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries [71.44210436913029]
  We propose a novel task of dense video captioning focusing on the generation of textual commentaries anchored with single timestamps. We present a challenging dataset consisting of almost 37k timestamped commentaries across 715.9 hours of soccer broadcast videos.
  arXiv  Detail & Related papers  (2023-04-10T13:08:03Z)
• GOAL: A Challenging Knowledge-grounded Video Captioning Benchmark for Real-time Soccer Commentary Generation [75.60413443783953]
  We present GOAL, a benchmark of over 8.9k soccer video clips, 22k sentences, and 42k knowledge triples for proposing a challenging new task setting as Knowledge-grounded Video Captioning (KGVC) Our data and code are available at https://github.com/THU-KEG/goal.
  arXiv  Detail & Related papers  (2023-03-26T08:43:36Z)
• Going for GOAL: A Resource for Grounded Football Commentaries [66.10040637644697]
  We present GrOunded footbAlL commentaries (GOAL), a novel dataset of football (or soccer') highlights videos with transcribed live commentaries in English. We 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.
  arXiv  Detail & Related papers  (2022-11-08T20:04:27Z)
• Temporally-Aware Feature Pooling for Action Spotting in Soccer Broadcasts [86.56462654572813]
  We focus our analysis on action spotting in soccer broadcast, which consists in temporally localizing the main actions in a soccer game. We propose a novel feature pooling method based on NetVLAD, dubbed NetVLAD++, that embeds temporally-aware knowledge. We train and evaluate our methodology on the recent large-scale dataset SoccerNet-v2, reaching 53.4% Average-mAP for action spotting.
  arXiv  Detail & Related papers  (2021-04-14T11:09:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.