研究人员开发了一种新颖的基于LLM的整体运动员画像框架，旨在克服传统手动或基础计算机视觉评估方法的局限性。该框架由LangGraph编排，整合了用于运动学追踪的计算机视觉和用于语义推理的Vision-Language Models，并特别符合印度体育局的协议。为了管理计算需求并防止幻觉，该框架采用了时间分块策略、LLM-as-a-Judge自我纠错循环以及使用ChromaDB进行自然语言查询的双持久化RAG管道。 AI
影响 该框架可以显著提高运动员人才识别和表现分析的客观性和可扩展性。
排序理由 该集群包含一篇详细介绍新颖AI框架的研究论文。
在 arXiv cs.MA (Multiagent) 阅读 →
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2606.28570v1 Announce Type: cross Abstract: Athlete assessment is a critical process for tracking physical progress and identifying elite talent. However, during mass recruitment drives, traditional methods rely on manual observation, which is inherently subjective and unsc…
Athlete assessment is a critical process for tracking physical progress and identifying elite talent. However, during mass recruitment drives, traditional methods rely on manual observation, which is inherently subjective and unscalable, or basic computer vision (CV) systems limi…