English(EN) Can Multimodal Large Language Models Understand Pathologic Movements? A Pilot Study on Seizure Semiology

多模态大语言模型在分析癫痫运动方面展现出潜力，表现优于传统模型

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-05 04:14

一项试点研究探讨了使用多模态大语言模型（MLLMs）分析癫痫视频中的病理性运动。研究发现，未经专门训练的MLLMs在许多癫痫特征的识别上优于传统的计算机视觉模型，尤其是在识别姿势和背景元素方面。虽然MLLMs在识别细微、高频运动方面存在困难，但有针对性的预处理技术提高了它们的性能，并且它们对预测的解释与专家推理高度一致。 AI

影响展示了将通用MLLMs应用于专业临床视频分析的潜力，为可解释的诊断辅助提供了途径。

排序理由这是一篇发表在arXiv上的研究论文，评估了现有模型的能力。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CV TIER_1 English(EN) · Lina Zhang, Tonmoy Monsoor, Mehmet Efe Lorasdagi, Prateik Sinha, Chong Han, Peizheng Li, Yuan Wang, Jessica Pasqua, Colin McCrimmon, Rajarshi Mazumder, Vwani Roychowdhury · 2026-05-06 04:00

Can Multimodal Large Language Models Understand Pathologic Movements? A Pilot Study on Seizure Semiology

arXiv:2605.03352v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated robust capabilities in recognizing everyday human activities, yet their potential for analyzing clinically significant involuntary movements in neurological disorders remain…
arXiv cs.CV TIER_1 English(EN) · Vwani Roychowdhury · 2026-05-05 04:14

Can Multimodal Large Language Models Understand Pathologic Movements? A Pilot Study on Seizure Semiology

Multimodal Large Language Models (MLLMs) have demonstrated robust capabilities in recognizing everyday human activities, yet their potential for analyzing clinically significant involuntary movements in neurological disorders remains largely unexplored. This pilot study evaluates…

报道来源 [2]

Can Multimodal Large Language Models Understand Pathologic Movements? A Pilot Study on Seizure Semiology

Can Multimodal Large Language Models Understand Pathologic Movements? A Pilot Study on Seizure Semiology

相关实体

相关话题