研究人员开发了用于改进复杂体育场景视频理解的新框架。TreeSoc 采用分层、树状搜索方法，并动态集成工具，将复杂查询分解为子任务，在 SoccerBench 基准测试上取得了最先进的成果。同时，SportMV-Agent 通过采用一种利用多视角信息以增强感知和推理的智能框架，解决了体育运动中单视角分析的局限性，在一个新引入的基准测试中表现优于现有的多模态大型语言模型。 AI
影响 这些进展可能带来更复杂的能够分析复杂视觉数据的AI系统，影响体育分析、内容审核和监控等领域。
排序理由 两篇介绍视频理解新框架和基准的研究论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2607.10990v1 Announce Type: new Abstract: Automated understanding of complex soccer scenarios from video remains a significant challenge for contemporary vision-language models (VLMs), which suffer from shallow cross-modal alignment and exhibit fundamental limitations in mu…
arXiv:2607.11844v1 Announce Type: new Abstract: 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 r…
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, spo…