首页> Journal of biomedical informatics> Cross-Modal self-supervised vision language pre-training with multiple objectives for medical visual question answering.

Cross-Modal self-supervised vision language pre-training with multiple objectives for medical visual question answering.

导出 LinkOut

翻译打印收藏纠错

第一作者： Gang,Liu

第一单位： College of Computer Science and Technology, Harbin Engineering University, Harbin, 150001, Heilongjiang, China. Electronic address: liugang@hrbeu.edu.cn.

作者： Gang,Liu ^[1] ; Jinlong,He ^[2] ; Pengfei,Li ^[3] ; Zixu,Zhao ^[4] ; Shenjun,Zhong ^[5]

作者单位： College of Computer Science and Technology, Harbin Engineering University, Harbin, 150001, Heilongjiang, China. Electronic address: liugang@hrbeu.edu.cn. ^[1] College of Computer Science and Technology, Harbin Engineering University, Harbin, 150001, Heilongjiang, China. Electronic address: hejinlong@hrbeu.edu.cn. ^[2] College of Computer Science and Technology, Harbin Engineering University, Harbin, 150001, Heilongjiang, China. Electronic address: pengfeili@hrbeu.edu.cn. ^[3] College of Computer Science and Technology, Harbin Engineering University, Harbin, 150001, Heilongjiang, China. Electronic address: zhaozixu@hrbeu.edu.cn. ^[4] Monash Biomedical Imaging, Monash University, Melbourne, 3800, Victoria, Australia. Electronic address: shenjun.zhong@monash.edu. ^[5]

关键词 Contrastive learning Cross-modal self-supervised Medical VQA Medical vision-language pre-training

医学主题词人类(Humans);算法(Algorithms);数据库, 事实型(Databases, Factual);自然语言处理(Natural Language Processing);图像处理, 计算机辅助(Image Processing, Computer-Assisted)

DOI 10.1016/j.jbi.2024.104748

PMID 39536998

发布时间 2025-08-06

翻译满意度评价：

准确一般字义偏差语意偏离译文作用小提交