研究人员开发了Open-KNEAD，一个用于从餐食图像估算营养成分的新框架。该系统采用代理分解方法，将每种食物项与数据库关联，以获得详细、可审计的记录。Open-KNEAD旨在以最小的用户努力提供准确的份量估算和可追溯的营养信息，并完全在本地运行以增强隐私。与直接估算方法和先前的方法相比，该框架在营养师验证的数据集上表现出改进的性能，并能恢复非美国菜肴的能量估算。 AI
影响 该框架可以为个人和临床医生提供更准确且注重隐私的饮食追踪。
排序理由 该集群包含一篇详细介绍新框架和方法的论文。
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:2607.12911v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are increasingly used for dietary assessment from meal images, where retrieval-augmented grounding was shown to sharpen nutrition estimates. However, we find this premise no longer holds for …
Multimodal Large Language Models (MLLMs) are increasingly used for dietary assessment from meal images, where retrieval-augmented grounding was shown to sharpen nutrition estimates. However, we find this premise no longer holds for current MLLMs. A modern MLLM's direct estimate n…