Real-Life Diabetogenic Database

Real-Life Diabetogenic (RLD) database is built for evaluating the cross-modal retrieval algorithm in real-life dietary environment, and it has 4500 multimodal pairs in total，where each images can be related to multiple texts and each text can be related to multiple images.For more details, you can refer to our paper: P. Zhou, C. Bai, J. Xia and S. Chen, "CMRDF: A Real-Time Food Alerting System Based on Multimodal Data," in IEEE Internet of Things Journal, doi: 10.1109/JIOT.2020.2996009.Please cite the above paper if you use this database.

真实生活糖尿病诱发（RLD）数据库旨在评估跨模态检索算法在实际饮食环境中的应用，该数据库包含总计4500组多模态对，其中每张图像均可关联多段文本，每段文本亦可关联多张图像。欲了解更多详细信息，请参阅我们的论文：周鹏，白晨，夏杰，陈硕，《CMRDF：一种基于多模态数据的实时食物警报系统》，发表于IEEE物联网杂志，DOI：10.1109/JIOT.2020.2996009。如使用本数据库，请引用上述论文。