May 13, 2023 · To address this limitation, we propose a unified Med-VLP framework based on Multi-task Paired Masking with Alignment (MPMA) to integrate the cross-modal alignment task into the joint image-text reconstruction framework to achieve more comprehensive cross-modal interaction, while a Global and Local Alignment (GLA) module is designed to assist sel...

Ke Zhang, Yan Yang, Jun Yu, Senior Member, IEEE, Hanliang Jiang, Jianping Fan, Qingming Huang, Fellow, IEEE, and Weidong Han Medical Vision-Language Pre-training (Med-VLP) methods have been proposed to learn universal representations from medical images and reports, benefiting downstream tas

To address this limitation, we propose a unified Med-VLP framework based on Multi-task Paired Masking with Alignment (MPMA) to integrate the cross-modal alignment task into the joint image-text reconstruction framework to achieve more comprehensive cross-modal interaction, while a Global and Local Alignment (GLA) module is designed to assist sel...

Apr 10, 2024 · 现为苏州大学计算机科学与技术学院副教授，硕士生导师，主要从事计算机视觉大模型和多模态大语言模型算法基础和应用研究。 本人于2019年本科毕业于天津大学，获得工学学士学位，2019年秋至清华大学硕博连读，于2024年1月博士毕业，并获得北京市优秀毕业生荣誉。 博士期间曾赴美国加州大学伯克利分校交换学习。...

GHFE combines the graph embedding, semantic embedding and visual features to form hybrid features, which are sent to a Transformer-based decoder for report generation. Extensive experiments on the MIMIC-CXR and IU X-Ray datasets demonstrate the effectiveness of our proposed approach.

‪清华大学博士‬ - ‪‪Cited by 42‬‬ - ‪Weakly supervised learning and data mining‬

Dec 31, 2023 · IEEE Trans. Multim. 25: 8212-8224 ( 2023) Bibliographic details on CFPNet: A Denoising Network for Complex Frequency Band Signal Processing.

Jie Wen, Ke Yan, Zheng Zhang, Yong Xu, Junqian Wang, Lunke Fei, Bob Zhang, Adaptive Graph Completion Based Incomplete Multi-view Clustering, IEEE Transactions on Multimedia (TMM), DOI: 10.1109/TMM.2020.3013408, 2020. This code has been evaluated on Matlab. If you find our approach useful in your research, please consider citing:

Semi-Supervised Medical Report Generation via Graph-Guided Hybrid Feature Consistency Ke Zhang, Hanliang Jiang Regional Medical Center for the National Institute of Respiratory Diseases, Sir Run Run Shaw Hospital, College of Medicine, Zhejiang University, Hangzhou, China , …

ORCID record for Ke Zhang. ORCID provides an identifier for individuals to use with their name as they engage in research, scholarship, and innovation activities.