[论文] Beyond the Single Camera: Agentic Multi-View Reasoning in Sports ...

论文概要

研究领域: CV
作者: Kerui Chen, Jinglu Wang, Xiaoyi Zhang, Yan Lu
发布时间: 2026-07-13
arXiv: 2607.11844

中文摘要

近期多模态大语言模型（MLLM）在单视角视频理解基准上表现强劲。但体育视频涉及密集遮挡、快速运动和复杂交互，难以从单一视角解决。实践中，体育赛事从多个摄像机角度录制，提供裁判使用的互补证据。然而，尚无现有基准评估MLLM在多视角体育视频理解上的表现。本文引入SportMV-Bench，一个综合基准，基于官方比赛录像构建，通过结合LLM生成、MLLM验证和人工过滤的专用流水线确保质量和一致性。包含787个多视角视频包和2592个问答对，跨越感知感知识别（PAR）、规则感知事件解读（REI）和裁决决策推理（ADR）三类。分析表明当前MLLM未能有效利用多视角信息，瓶颈在于细粒度视觉感知和视角选择而非逻辑推理或领域知识。提出SportMV-Agent，一种主动视角选择、感知工具执行和证据grounded推理的迭代循环智能体框架，相比最强MLLM基线实现14.46%的相对提升。

原文摘要

Recent Multimodal Large Language Models (MLLMs) achieve strong performance on single-view video understanding benchmarks. However, sports videos involve dense occlusion, rapid motion, and complex interactions that are difficult to resolve from a single viewpoint. In practice, sports events are recorded from multiple camera angles, providing complementary evidence used by referees. Yet, no existing benchmark evaluates MLLMs on multi-view sports video understanding. To address this gap, we introduce SportMV-Bench, a comprehensive benchmark built from official match recordings, through a dedicated pipeline combining LLM-based generation, MLLM-based verification, and human filtering to ensure quality and consistency. SportMV-Bench containing 787 multi-view video bundles and 2592 question-answe...

自动采集于 2026-07-15

#论文 #arXiv #CV #小凯