一、基本情况
许铮铧,男,博士,教授。河北省海外高层次人才“百人计划”省级特聘专家,河北省“优青”获得者,英国牛津大学计算机系博士、博士后、客座研究员、外聘博导,2014-16年间担任英国牛津大学计算机系助理研究员,2017-18年间担任英国牛津大学计算机系副研究员、博士生导师,2018年起任河北工业大学教授、博导。
主要从事人工智能、深度学习、强化学习、医学影像智能计算等方面研究,近五年主持国家自然科学基金项目2项、省部级高水平项目3项,近五年以第一/通讯作者身份在CVPR、NeurIPS等CCF A/B类国际顶会发表论文近20篇、在TNNLS、MedIA等SCI一/二区期刊发表论文近10篇,单篇论文最高引用330余次。长期担任AAAI、IJCAI等人工智能国际顶会程序委员会(高级)委员和分会主席,是中国计算机学会机器视觉专委会(CCF-CV)执行委员、医学图像计算青年研讨会(MICS)委员、中国计算机学会青年计算机科技论坛天津分论坛(YOCSEF天津)学术秘书、中国生物医学工程学会医学影像工程与技术分会青年委员、河北省数理医学学会健康大数据专委会常务委员、河北省生物医学工程学会医工融合成果转化专委会常委。
二、博导所属学科
1、083100 生物医学工程
研究方向:05 智能医疗与健康大数据建模
2、080800 电气工程
研究方向:05 生物电工技术
三、硕导所属学科
1、083100/085409 生物医学工程
研究方向:01智能医学与健康工程
2、080800/085801电气工程
研究方向一:05生物电工技术
研究方向二:06电工装备可靠性与智能化(交叉培养方向)
3、085410人工智能
研究方向:01人工智能模型与理论
四、主持、参与的科研及教研项目情况(含获奖情况)
4.1主持和参与的主要科研项目
(1)国家自然科学基金面上项目,2023-2026,主持
(2)国家自然科学基金青年项目,2020-2022,主持
(3)河北省引进海外高层次人才“百人计划”资助项目,2020-2022,主持
(4)河北省自然科学基金优秀青年科学基金项目,2021-2023,主持
(5)天津市自然科学基金青年项目,2019-2022,主持
(6)海南省重点研发计划社会发展方向项目,2022-2024,第一主研
(7)河北工业大学元光学者自主项目,2018-2023,主持
4.2获奖情况
(1)河北省引进海外高层次人才“百人计划”省级特聘专家
(2)谷歌全球博士奖研金提名
(3)英国牛津大学Jason Hu博士奖学金
(4)Australasian Database Conference Runner-up for Best Paper Award(最佳论文奖)
五、近年来发表代表性论文情况(仅限第一作者或通讯作者),主编或参编的教材、专著情况,获得专利情况等
5.1十篇代表作
[1] Yuhang Song*, Beren Millidge, Tommaso Salvatori, Thomas Lukasiewicz*, Zhenghua Xu* (通讯作者), Rafal Bogacz*. Inferring Neural Activity Before Plasticity: A Foundation for Learning Beyond Backpropagation. Nature Neuroscience第三轮返修审稿中. (Nature子刊, IF: 28.771)
[2] Shuo Zhang, Jiaojiao Zhang, Biao Tian, Thomas Lukasiewicz, Zhenghua Xu* (通讯作者). Multi-Modal Contrastive Mutual Learning and Pseudo-Label Re-Learning for Semi-Supervised Medical Image Segmentation. Medical Image Analysis, 2023. (SCI一区, IF: 13.828)
[3] Jianfeng Wang, Thomas Lukasiewicz, Xiaolin Hu, Jianfei Cai, Zhenghua Xu* (通讯作者). RSG: A Simple Yet Effective Module for Learning Imbalanced Datasets. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021. (CCF-A类人工智能国际顶级会议)
[4] Yixin Su, Rui Zhang*, Sarah Erfani, Zhenghua Xu* (通讯作者). Detecting Beneficial Feature Interactions for Recommender Systems via Graph Neural Networks. In Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI), 2021. (CCF-A类人工智能国际顶级会议)
[5] Yuhang Song, Thomas Lukasiewicz, Zhenghua Xu* (通讯作者), Rafal Bogacz. Can the Brain Do Backpropagation? -- Exact Implementation of Backpropagation in Predictive Coding Networks. In Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS), 2020. (CCF-A类人工智能国际顶级会议)
[6] Yuhang Song, Andrzej Wojcicki, Thomas Lukasiewicz, Jianyi Wang, Abi Aryan, Zhenghua Xu* (通讯作者), Mai Xu, Zihan Ding and Lianlong Wu. Arena: A General Evaluation Platform and Building Toolkit for Multi−Agent Intelligence. In Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI), 2020. (CCF-A类人工智能国际顶级会议)
[7] Yuhang Song, Jianyi Wang, Thomas Lukasiewicz, Zhenghua Xu* (通讯作者), Shangtong Zhang, Andrzej Wojcicki and Mai Xu. Mega−Reward: Achieving Human−Level Play without Extrinsic Rewards. In the proceeding of AAAI Conference on Artificial Intelligence (AAAI), 2020. (CCF-A类人工智能国际顶级会议)
[8] Yuhang Song, Jianyi Wang, Thomas Lukasiewicz, Zhenghua Xu* (通讯作者), Mai Xu. Diversity-Driven Extensible Hierarchical Reinforcement Learning. In the proceeding of AAAI Conference on Artificial Intelligence (AAAI), 2019. (CCF-A类人工智能国际顶级会议)
[9] Zhenghua Xu* (第一作者兼通讯作者), Cheng Chen, Thomas Lukasiewicz, Yishu Miao and Xiangwu Meng. Tag-Aware Personalized Recommendation Using a Hybrid Deep Model. In the proceeding of International Joint Conference on Artificial Intelligence (IJCAI), 2017. (CCF-A类人工智能国际顶级会议)
[10] Andy Yuan Xue, Rui Zhang, Yu Zheng, Xing Xie, Jin Huang and Zhenghua Xu. Destination Prediction by Sub-trajectory Synthesis and Privacy Protection against Such Prediction. In the proceeding of 29th IEEE International Conference on Data Engineering (ICDE), 2013. (CCF-A类数据挖掘国际顶级会议, Google Scholar引用333次)
5.2其他CCF- A/B类国际顶级会议论文
[11] Tommaso Salvatori‚ Yuhang Song*‚ Zhenghua Xu‚ Thomas Lukasiewicz and Rafal Bogacz. Reverse Differentiation via Predictive Coding. In Proceedings of the 36th AAAI Conference on Artificial Intelligence (AAAI), 2022. (CCF-A类人工智能国际顶级会议)
[12] Tommaso Salvatori#, Yuhang Song#*, Yujian Hong, Simon Frieder, Lei Sha, Zhenghua Xu, Rafal Bogacz and Thomas Lukasiewicz. Associative Memories via Predictive Coding. In Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS), 2021. (CCF-A类人工智能国际顶级会议)
[13] Gang Xu, Shengxin Wang, Zhenghua Xu* (通讯作者), Thomas Lukasiewicz. Adaptive-Masking Policy with Deep Reinforcement Learning for Self-Supervised Medical Image Segmentation. Accepted to publish in Proceedings of the IEEE International Conference on Multimedia & Expo (ICME), 2023. (CCF-B类机器视觉国际顶级会议)
[14] Ruizhi Wang, Xiangtao Wang, Zhenghua Xu* (通讯作者), Wenting Xu, Junyang Chen, Thomas Lukasiewicz. MvCo-DoT: Multi-View Contrastive Domain Transfer Network for Medical Report Generation. Accepted to publish in Proceedings of the 48th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023. (CCF-B类信号处理国际顶级会议)
[15] Xiangtao Wang, Ruizhi Wang, Biao Tian, Jiaojiao Zhang, Shuo Zhang, Junyang Chen, Thomas Lukasiewicz, Zhenghua Xu* (通讯作者). MPS-AMS: Masked Patches Selection and Adaptive Masking Strategy Based Self-Supervised Medical Image Segmentation. Accepted to publish in Proceedings of the 48th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023. (CCF-B类信号处理国际顶级会议)
[16] Hexiang Zhang, Zhenghua Xu* (通讯作者), Dan Yao, Shuo Zhang, Junyang Chen, Thomas Lukasiewicz. Multi-Head Feature Pyramid Networks for Breast Mass Detection. Accepted to publish in Proceedings of the 48th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023. (CCF-B类信号处理国际顶级会议)
[17] Zhenghua Xu*# (第一作者兼通讯作者), Di Yuan#, Thomas Lukasiewicz, Cheng Chen, Yishu Miao and Guizhi Xu*. Hybrid Deep-Semantic Matrix Factorization for Tag-Aware Personalized Recommendation. In Proceedings of the 45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020. (CCF-B类信号处理国际顶级会议)
[18] Zhenghua Xu (第一作者), Chang Qi and Guizhi Xu*. Semi-Supervised Attention -Guided CycleGAN for Data Augmentation on Medical Images. In the proceeding of IEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM), 2019. (CCF-B类生物信息国际顶级会议)
[19] Lei Wang, Bo Wang, Zhenghua Xu* (通讯作者). Tumor Segmentation Based on Deeply Supervised Multi-Scale U-Net. In the proceeding of IEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM), 2019. (CCF-B类生物信息国际顶级会议)
[20] Bo Li, Zehua Cheng, Zhenghua Xu* (通讯作者), Wei Ye, Thomas Lukasiewicz, Shikun Zhang. Long Text Analysis Using Sliced Recurrent Neural Networks with Breaking Point Information Enrichment. In the proceeding of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019. (CCF-B类信号处理国际顶级会议)
[21] Cheng Chen, Thomas Lukasiewicz, Xiangwu Meng and Zhenghua Xu. Location-Aware News Recommendation Using Deep Localized Semantic Analysis. In the proceeding of 22nd International Conference on Database Systems for Advanced Applications (DASFAA), 2017. (CCF-B类数据库国际顶级会议)
[22] Zhenghua Xu (第一作者), Cheng Chen, Thomas Lukasiewicz, Yishu Miao and Xiangwu Meng. Tag-Aware Personalized Recommendation Using a Deep-Semantic Similarity Model with Negative Sampling. In the proceeding of 25th ACM International Conference on Information and Knowledge Management (CIKM), 2016. (CCF-B类数据处理国际顶级会议)
[23] Zhenghua Xu (第一作者), Rui Zhang, Ramamohanarao Kotagiri and Udaya Parampalli. An Adaptive Online Algorithm for Time Series Segmentation with Error Bound Guarantee. In the proceeding of 15th International Conference on Extending Database Technology (EDBT), 2012. (CCF-B类数据库国际顶级会议)
[24] Jianzhong Qi, Zhenghua Xu, Yuan Xue and ZeyiWen. A Branch and Bound Method for Min-dist Location Selection Queries. In the proceeding of 23rd Australasian Database Conference (ADC), 2012. (Runner-up Best Paper Award,最佳论文奖)
5.3 其他SCI一/二区期刊论文
[25] Junyang Chen, Zhiguo Gong*, Wei Wang, Cong Wang*, Zhenghua Xu, Jianming Lv, Xueliang Li, Kaishun Wu, Weiwen Liu. Adversarial Caching Training: Unsupervised Inductive Network Representation Learning on Large-Scale Graphs. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021. (SCI一区, IF: 10.451 )
[26] Zhenghua Xu (第一作者), Shijie Liu, Di Yuan, Lei Wang, Junyang Chen, Thomas Lukasiewicz, Zhigang Fu, Rui Zhang. ω-Net: Dual Supervised Medical Image Segmentation with Multi-Dimensional Self-Attention and Diversely-Connected Multi-Scale Convolution. Neurocomputing, 2022. (SCI二区Top, IF: 5.779)
[27] Haozhe Lin, Yushun Fan, Jia Zhang, Bing Bai, Zhenghua Xu, Thomas Lukasiewicz. Toward Knowledge as a Service (KaaS): Predicting Popularity of Knowledge Services Leveraging Graph Neural Networks. In IEEE Transactions on Service Computing (TSC), 2022. (CCF A类国际顶级期刊, SCI二区Top, IF: 8.216)
[28] Di Yuan, Yunxin Liu*, Zhenghua Xu* (通讯作者), Yuefu Zhan, Junyang Chen, Thomas Lukasiewicz. Painless and Accurate Medical Image Analysis Using Deep Reinforcement Learning with Task-Oriented Homogenized Automatic Pre-Processing. Computers in Biology and Medicine, 2023. (SCI二区, IF: 6.698)
[29] Zhenghua Xu* (第一作者兼通讯作者), Tianrun Li, Yunxin Liu, Yuefu Zhan*, Junyang Chen, Thomas Lukasiewicz. PAC-Net: Multi-Pathway FPN with Position Attention Guided Connections and Vertex Distance IoU for 3D Medical Image Detection. Frontiers in Bioengineering and Biotechnology, 2023. (SCI二区, IF: 6.064)
[30] Junyang Chen, Mengzhu Wang, Haodi Zhang, Zhenghua Xu, Xueliang Li, Zhiguo Gong, Kaishun Wu, Victor C. M. Leung. IRLM: Inductive Representation Learning Model for Personalized POI Recommenda tion. IEEE Transactions on Computational Social System, 2022. (SCI二区, IF: 4.747)
5.4 专利申请与授权情况
[1] 针对分割任务的医学影像特征增强方法,许铮铧、齐畅、徐桂芝,已授权,专利号:ZL202011356102.9,授权公告日:2022.07.01。
[2] 基于全视野数字切片的病人级别肿瘤智能诊断方法,赵丹、徐桂芝、许铮铧,已授权,专利号:ZL202011137309.7,授权公告日:2022.08.30。
[3] 一种带有尺度增强和注意力融合的医疗图像病灶检测算法,许铮铧、张旭东,已申请,申请号:202210078271.3,申请日期:2022.01.24。
[4] 居民短期电力负荷自动化预测方法,许铮铧、余周涛,已申请,申请号:202210077357.4,申请日期:2022.01.24。
[5] 金字塔和损失函数增强的电力系统绝缘及缺陷检测网络,许铮铧、王博,已申请,申请号:202210036799.4,申请日期:2022.01.13。
[6] 基于多模态自监督的医学影像分割方法,许铮铧、张娇娇,已申请,申请号:202211374925.3,申请日期:2022.11.04。
[7] 针对医学影像分割任务的生成式模态补足方法,许铮铧、姚丹,已申请,申请号:202211533192.3,申请日期:2022.12.01。
[8] 基于因果奖励的多任务自监督强化学习,许铮铧、周杰,已申请,申请号:202310048598.0,申请日期:2023.01.31。
六、联系人:许铮铧, 联系方式:zhenghua.xu@hebut.edu.cn