# BoxComm: Benchmarking Category-Aware Commentary Generation and Narration Rhythm in Boxing

arXiv: https://arxiv.org/abs/2604.04419 · HTML: https://mlsanity.com/paper/2604.04419/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 20 of its 38 references that are in the map.
- First posted on arXiv 6 Apr 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 20 of 20)

- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [Humans in 4D: Reconstructing and Tracking Humans with Transformers](https://mlsanity.com/paper/2305.20091/) (2023)
- [LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training](https://mlsanity.com/paper/2509.23661/) (2025)
- [SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos](https://mlsanity.com/paper/1804.04527/) (2018)
- [SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos](https://mlsanity.com/paper/2011.13367/) (2020)
- [StreamingVLM: Real-Time Understanding for Infinite Video Streams](https://mlsanity.com/paper/2510.09608/) (2025)
- [SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries](https://mlsanity.com/paper/2304.04565/) (2023)
- [MatchTime: Towards Automatic Soccer Game Commentary Generation](https://mlsanity.com/paper/2406.18530/) (2024)
- [GOAL: A Challenging Knowledge-grounded Video Captioning Benchmark for Real-time Soccer Commentary Generation](https://mlsanity.com/paper/2303.14655/) (2023)
- [SportR: A Benchmark for Multimodal Large Language Model Reasoning in Sports](https://mlsanity.com/paper/2511.06499/) (2025)
- [TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generation](https://mlsanity.com/paper/2504.17365/) (2025)
- [Language and Multimodal Models in Sports: A Survey of Datasets and Applications](https://mlsanity.com/paper/2406.12252/) (2024)
- [FineBadminton: A Multi-Level Dataset for Fine-Grained Badminton Video Understanding](https://mlsanity.com/paper/2508.07554/) (2025)
- [SCBench: A Sports Commentary Benchmark for Video LLMs](https://mlsanity.com/paper/2412.17637/) (2024)
- [BoxMAC -- A Boxing Dataset for Multi-label Action Classification](https://mlsanity.com/paper/2412.18204/) (2024)
- [BoxMind: Closed-loop AI strategy optimization for elite boxing validated in the 2024 Olympics](https://mlsanity.com/paper/2601.11492/) (2026)
- [TennisExpert: Towards Expert-Level Analytical Sports Video Understanding](https://mlsanity.com/paper/2603.13397/) (2026)

## Abstract (arXiv)

Recent multimodal large language models (MLLMs) have shown strong capabilities in general video understanding, driving growing interest in automatic sports commentary generation. However, existing benchmarks for this task focus exclusively on team sports such as soccer and basketball, leaving combat sports entirely unexplored. Notably, combat sports present distinct challenges: critical actions unfold within milliseconds with visually subtle yet semantically decisive differences, and professional commentary contains a substantially higher proportion of tactical analysis compared to team sports. In this paper, we present BoxComm, a large-scale dataset comprising 445 World Boxing Championship match videos with over 52K commentary sentences from professional broadcasts. We propose a structured commentary taxonomy that categorizes each sentence into play-by-play, tactical, or contextual, providing the first category-level annotation for sports commentary benchmarks. Building on this taxonomy, we introduce two novel and complementary evaluations tailored to sports commentary generation: (1) category-conditioned generation, which evaluates whether models can produce accurate commentary of a specified type given video context; and (2) commentary rhythm assessment, which measures whether freely generated commentary exhibits appropriate temporal pacing and type distribution over continuous video segments, capturing a dimension of commentary competence that prior benchmarks have not addressed. Experiments on multiple state-of-the-art MLLMs reveal that current models struggle on both evaluations. We further propose EIC-Gen, an improved baseline incorporating detected punch events to supply structured action cues, yielding consistent gains and highlighting the importance of perceiving fleeting and subtle events for combat sports commentary.