# Towards Automatic Soccer Commentary Generation with Knowledge-Enhanced Visual Reasoning

arXiv: https://arxiv.org/abs/2604.00057 · HTML: https://mlsanity.com/paper/2604.00057/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 29 of its 53 references that are in the map.
- First posted on arXiv 31 Mar 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 29 of 29)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023)
- [SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos](https://mlsanity.com/paper/2011.13367/) (2020)
- [KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation](https://mlsanity.com/paper/2409.13731/) (2024)
- [SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries](https://mlsanity.com/paper/2304.04565/) (2023)
- [A Unified Framework for Shot Type Classification Based on Subject Centric Lens](https://mlsanity.com/paper/2008.03548/) (2020)
- [MatchTime: Towards Automatic Soccer Game Commentary Generation](https://mlsanity.com/paper/2406.18530/) (2024)
- [How Good is my Video LMM? Complex Video Reasoning and Robustness Evaluation Suite for Video-LMMs](https://mlsanity.com/paper/2405.03690/) (2024)
- [GOAL: A Challenging Knowledge-grounded Video Captioning Benchmark for Real-time Soccer Commentary Generation](https://mlsanity.com/paper/2303.14655/) (2023)
- [BIDER: Bridging Knowledge Inconsistency for Efficient Retrieval-Augmented LLMs via Key Supporting Evidence](https://mlsanity.com/paper/2402.12174/) (2024)
- [Towards Universal Soccer Video Understanding](https://mlsanity.com/paper/2412.01820/) (2024)
- [Multi-Agent System for Comprehensive Soccer Understanding](https://mlsanity.com/paper/2505.03735/) (2025)
- [TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generation](https://mlsanity.com/paper/2504.17365/) (2025)
- [SoccerNet-Echoes: A Soccer Game Audio Commentary Dataset](https://mlsanity.com/paper/2405.07354/) (2024)
- [Jersey Number Recognition using Keyframe Identification from Low-Resolution Broadcast Videos](https://mlsanity.com/paper/2309.06285/) (2023)
- [Knowledge Enhanced Sports Game Summarization](https://mlsanity.com/paper/2111.12535/) (2021)
- [Domain Adaptation of VLM for Soccer Video Understanding](https://mlsanity.com/paper/2505.13860/) (2025)
- [Automatic Pass Annotation from Soccer VideoStreams Based on Object Detection and LSTM](https://mlsanity.com/paper/2007.06475/) (2020)
- [MMSys'22 Grand Challenge on AI-based Video Production for Soccer](https://mlsanity.com/paper/2202.01031/) (2022)
- [SoccerRAG: Multimodal Soccer Information Retrieval via Natural Queries](https://mlsanity.com/paper/2406.01273/) (2024)

## Built on by (most cited first, 1 of 1)

- [StreamSoccer: Event-Driven Memory for Streaming Soccer Commentary](https://mlsanity.com/paper/2608.19723/) (2026)

## Abstract (arXiv)

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