个人简介

博士，副教授，硕士生导师。中国科学院大学和香港城市大学双博士学位，于2018年7月加入3044am永利集团3044noc与北京人工智能研究院，主要进行包括计算机视觉与自然语言处理在内的人工智能领域关键技术理论和应用研究，目前在IEEE TIP、Pattern Recognition、ACM MM、EMNLP、COLING等国际知名期刊和会议上发表论文多篇。主持并参与多项国家自然科学基金项目，2022年获得北京市高层次留学人才回国资助。

主要研究方向

计算机视觉、自然语言处理、多模态大模型等。

教育简历

2015/09-2018/06，香港城市大学，计算机应用技术专业，博士（联培）

2014/09-2018/06，中国科学院大学，计算机应用技术专业，博士

2010/09-2014/06，中国科学院大学，计算机应用技术专业，硕士

2006/09-2010/06，郑州大学，生物医学工程专业，学士

课程教学

学术前沿、学术写作

科研项目

1．国家自然科学基金青年项目，基于脑血管疾病颅脑影像的医学报告自动生成及病灶定位研究，主持。

2．北京市教育委员会科技计划一般项目,基于时序三维影像的病变趋势预测报告生成方法研究，主持。

3．国家自然科学基金联合基金项目重点支持项目，面向社会媒体信息的视觉协同计算与聚焦推理，参与。

代表性研究成果

1.Chengxin Zheng, Junzhong Ji, Yanzhao Shi, Xiaodan Zhang, Liangqiong Qu. See Detail Say Clear: Towards Brain CT Report Generation via Pathological Clue-driven Representation Learning. EMNLP 2024. (NLP领域顶会, CAAI-A, CCF-B)

2.Xiaodan Zhang, Shixin Dou, Junzhong Ji, Ying Liu, Zheng Wang. Co-occurrence Relationship Driven Hierarchical Attention Network for Brain CT Report Generation. IEEE Transactions on Emerging Topics in Computational Intelligence. 2024. (SCI一区期刊)

3.Yanzhao Shi, Junzhong Ji, Xiaodan Zhang, Ying Liu, Zheng Wang, Huimin Xu. Prior tissue knowledge-driven contrastive learning for brain CT report generation. Multimedia Systems, 2024 (30):98. (SCI一区期刊)

4.Qingya Shen, Yanzhao Shi, Xiaodan Zhang, Junzhong Ji, Ying Liu, Huimin Xu. GHCL: Gaussian heuristic curriculum learning for Brain CT report generation. Multimedia Systems, 2024 (30):69. (SCI一区期刊)

5.Xiaodan Zhang, Sisi Yang, Yanzhao Shi, Junzhong Ji, Ying Liu, Zheng Wang, Huimin Xu; Weakly Guided Attention Model with Hierarchical Interaction for Brain CT Report Generation, Computers in Biology and Medicine (CIBM), 2023:107650. (SCI一区期刊)

6.Yanzhao Shi, Junzhong Ji, Xiaodan Zhang, Liangqiong Qu, and Ying Liu. Granularity Matters: Pathological Graph-driven Cross-modal Alignment for Brain CT Report Generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023:6617–6630. (NLP领域顶会, CAAI-A, CCF B)

7.Xiao Song, Xiaodan Zhang, Junzhong Ji, Ying Liu, Pengxu Wei. Cross-modal Contrastive Attention Model for Medical Report Generation. In Proceedings of the 29th International Conference on Computational Linguistics (COLING), 2022: 2388-2397. (NLP领域顶会, CCF-B)

8.Junzhong Ji, Mingzhan Wang, Xiaodan Zhang, Minglong Lei, Liangqiong Qu, Relation constraint self-attention for image captioning, Neurocomputing, vol. 501, 2022 (501): 778-789. (SCI一区期刊)

9.Junzhong Ji, Zhuoran Du, Xiaodan Zhang. Divergent-convergent Attention for Image Captioning. Pattern Recognition, 2021 (115): 107928. (中科院SCI一区期刊)

10.Sisi Yang, Junzhong Ji, Xiaodan Zhang, Ying Liu, Zheng Wang, Weakly Guided Hierarchical Encoder-Decoder Network for Brain CT Report Generation. IEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM), 2021: 568-573. (生物信息学领域顶会, CCF-B)

11.Junzhong Ji, Cheng Xu, Xiaodan Zhang, Boyue Wang, Xinhang Song. Spatio-temporal Memory Attention for Image Captioning. IEEE Transactions on Image Processing (TIP), 2020 (29): 7615-7628. (CCF-A, 中科院SCI一区)

12.Xiaodan Zhang, Shengfeng He, Xinhang Song, Rynson W. H. Lau, Jianbin Jiao, Qixiang Ye, Image Captioning via Semantic Element Embedding. Neurocomputing, 2020 (395): 212-221. (SCI一区)