FineBadminton: A Multi-Level Dataset for Fine-Grained Badminton Video Understanding

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: He, Xusheng, Liu, Wei, Ma, Shanshan, Liu, Qian, Ma, Chenghao, Wu, Jianlong
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918121247342592
author He, Xusheng
Liu, Wei
Ma, Shanshan
Liu, Qian
Ma, Chenghao
Wu, Jianlong
author_facet He, Xusheng
Liu, Wei
Ma, Shanshan
Liu, Qian
Ma, Chenghao
Wu, Jianlong
contents Fine-grained analysis of complex and high-speed sports like badminton presents a significant challenge for Multimodal Large Language Models (MLLMs), despite their notable advancements in general video understanding. This difficulty arises primarily from the scarcity of datasets with sufficiently rich and domain-specific annotations. To bridge this gap, we introduce FineBadminton, a novel and large-scale dataset featuring a unique multi-level semantic annotation hierarchy (Foundational Actions, Tactical Semantics, and Decision Evaluation) for comprehensive badminton understanding. The construction of FineBadminton is powered by an innovative annotation pipeline that synergistically combines MLLM-generated proposals with human refinement. We also present FBBench, a challenging benchmark derived from FineBadminton, to rigorously evaluate MLLMs on nuanced spatio-temporal reasoning and tactical comprehension. Together, FineBadminton and FBBench provide a crucial ecosystem to catalyze research in fine-grained video understanding and advance the development of MLLMs in sports intelligence. Furthermore, we propose an optimized baseline approach incorporating Hit-Centric Keyframe Selection to focus on pivotal moments and Coordinate-Guided Condensation to distill salient visual information. The results on FBBench reveal that while current MLLMs still face significant challenges in deep sports video analysis, our proposed strategies nonetheless achieve substantial performance gains. The project homepage is available at https://finebadminton.github.io/FineBadminton/.
format Preprint
id arxiv_https___arxiv_org_abs_2508_07554
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FineBadminton: A Multi-Level Dataset for Fine-Grained Badminton Video Understanding
He, Xusheng
Liu, Wei
Ma, Shanshan
Liu, Qian
Ma, Chenghao
Wu, Jianlong
Multimedia
Fine-grained analysis of complex and high-speed sports like badminton presents a significant challenge for Multimodal Large Language Models (MLLMs), despite their notable advancements in general video understanding. This difficulty arises primarily from the scarcity of datasets with sufficiently rich and domain-specific annotations. To bridge this gap, we introduce FineBadminton, a novel and large-scale dataset featuring a unique multi-level semantic annotation hierarchy (Foundational Actions, Tactical Semantics, and Decision Evaluation) for comprehensive badminton understanding. The construction of FineBadminton is powered by an innovative annotation pipeline that synergistically combines MLLM-generated proposals with human refinement. We also present FBBench, a challenging benchmark derived from FineBadminton, to rigorously evaluate MLLMs on nuanced spatio-temporal reasoning and tactical comprehension. Together, FineBadminton and FBBench provide a crucial ecosystem to catalyze research in fine-grained video understanding and advance the development of MLLMs in sports intelligence. Furthermore, we propose an optimized baseline approach incorporating Hit-Centric Keyframe Selection to focus on pivotal moments and Coordinate-Guided Condensation to distill salient visual information. The results on FBBench reveal that while current MLLMs still face significant challenges in deep sports video analysis, our proposed strategies nonetheless achieve substantial performance gains. The project homepage is available at https://finebadminton.github.io/FineBadminton/.
title FineBadminton: A Multi-Level Dataset for Fine-Grained Badminton Video Understanding
topic Multimedia
url https://arxiv.org/abs/2508.07554