Doctoral Consortium
Topic: Recent
Trends in Deep Learning based Computer
Vision
主题：基于深度学习的计算机视觉前沿技术
Scope and Aim: Recently, deep
learning techniques like CNN and
transformer have been widely applied in
computer vision and achieved great
success in image classification, object
detection and segmentation. However,
annotation cost of large amount of data
has been a significant obstacle to real
applications of these approaches. On the
other hand, cross-modality models like
CLIP (Contrastive Language-Image
Pretraining) pretrained on large scale
datasets are publicly available. This
consortium aims to bring PhD students
working is this area to share their most
recent research progresses, exchange
ideas and discuss possible solutions and
trends toward the issues related with DL
technologies. Academic experiences of
the mentor will also be shared and the
students could also discuss and receive
possible advices for the early career
development in academics.
范围和目标：近年来，类似CNN以及Transformer的深度学习技术在计算机视觉领域取得了巨大成功，在很多诸如图像分类、物体检测与分割任务上都获得了很好的性能。但对于大量标注数据的需求，始终是深度学习在实际应用中的遇到的难点之一。另一方面，诸如CLIP等大规模预训练模型也给下游任务提供了一个很好的基础架构。该论坛的目的是给博士生们提供一个计算机视觉领域深度学习发展趋势的讨论平台，通过各位参与者对自己代表性研究工作的介绍和交流，互相学习、获得灵感。导师也会分享自己学术研究的经历和经验，并为博士毕业后的早期学术职业生涯发展，提供可能的建议。
Mentor: Prof. Linlin Shen, Shenzhen
University, China
导师: 深圳大学沈琳琳教授
Linlin Shen is currently a Pengcheng
Scholar Distinguished Professor at
School of Computer Science and Software
Engineering, Shenzhen University,
Shenzhen, China. He is also a Honorary
professor at School of Computer Science,
University of Nottingham,UK. He serves
as the director of Computer Vision
Institute, AI Research Center for
Medical Image Analysis and Diagnosis and
China-UK joint research lab for visual
information processing. He also serves
as the Co-Editor-in-Chief of the IET
journal of Cognitive Computation and
Systems. Prof. Shen received the BSc and
MEng degrees from Shanghai Jiaotong
University, Shanghai, China, and the
Ph.D. degree from the University of
Nottingham, Nottingham, U.K. He was a
Research Fellow with the University of
Nottingham, working on MRI brain image
processing. His research interests
include deep learning, facial
recognition, analysis/synthesis and
medical image processing. Prof. Shen is
listed as the “Most Cited Chinese
Researchers” by Elsevier, and listed in
a ranking of the “Top 2% Scientists in
the World” by Stanford University. He
received the Most Cited Paper Award from
the journal of Image and Vision
Computing. His cell classification
algorithms were the winners of the
International Contest on Pattern
Recognition Techniques for Indirect
Immunofluorescence Images held by ICIP
2013 and ICPR 2016.
沈琳琳，教授，上海交通大学学士、硕士。英国诺丁汉大学博士。现为深圳大学计算机与软件学院“鹏城学者”特聘教授、英国诺丁汉大学计算机学院荣誉教授、深圳大学计算机视觉研究所所长、深圳大学医学影像智能分析与诊断研究中心主任、广东省教育厅中英合作视觉信息处理实验室主任，IET
Cognitive Computation and
Systems期刊常务副主编。他的研究方向主要为深度学习理论及其在人脸识别/分析以及医学图像分析上的应用。沈教授曾入选Elsevier中国高被引学者榜单，斯坦福大学全球前2%顶尖科学家榜单，获国际期刊《Image
and Vision
Computing》最多他引论文奖。他开发的细胞荧光图像分类算法连续获得IEEE
ICIP 2013、ICPR 2016国际细胞图像分类算法大赛冠军。
Topic: Medical
Image/Video Deep Learning
主题：医学图像/视频深度学习
Scope and Aim: With the
development of artificial intelligence
and big data processing in clinical
medicine, medical image/video deep
learning based on ultrasound images,
endoscopy images, X-ray angiography has
gradually achieved better performance in
minimally invasive diagnosis and
treatment than traditional medical
imaging and experienced doctors.
However, the challenging problem caused
by low contrast image contents disturbed
with the interferences of complex noises
and abnormal artifacts, inaccurate and
inaccessible labeled training data,
heterogenous and indescribable
spatiotemporal features, calls for a
great breakthrough of methodology in
balancing the real time, accuracy and
robustness of deep learning performance.
In the field of deep learning, on the
one hand, model-driven deep learning
such as algorithm unrolling has provided
an interpretable weakly-supervised deep
learning for exploiting the dual
advantages of model optimization and
data-driven machine learning. On the
other hand, video deep learning based on
convolutional neural networks and visual
transformer also has paved the way for a
promising methodology. The purpose of
this forum is to provide a platform for
doctoral students to discuss the
frontier development trend of medical
image/video deep learning. Through the
introduction and exchange of
participants' representative research
work, they can learn and inspire each
other and promote the transformation of
application scenarios to solve practical
clinical problems. The tutor will also
share research experience on how to
challenge clinical problems and develop
independent innovation for career
development after graduation.
范围和目标：随着人工智能和大数据处理在临床医学中的应用发展，基于超声图像、内窥镜图像、X-ray血管造影成像等模式的视频数据深度学习在微创诊疗中逐渐得到了比基于传统医学成像和有经验医生更好的性能。但医学图像及视频深度学习存在复杂噪声、低对比度及异常信号干扰，医生精确标注训练数据极难获取，图像时空先验信息很难表达的极大挑战，决定了医学视频图像弱监督深度学习等研究在解决实时性、准确性和鲁棒性瓶颈问题时急需寻找新的方法学突破。而在深度学习领域，一方面数据驱动深度学习结合模型优化，如优化算法深度展开(algorithm
unrolling)，为深度学习结合模型优化和数据驱动的双重优势，在弱监督可解释深度学习领域开拓了很好的研究方向，另一方面基于卷积网络和基于视
觉Transformer相结合的视频深度学习也开创了极具潜力的发展思路。本该论坛目的是给博士生们提供一个医学图像/视频深度学习前沿发展趋势的讨论平台，通过各位参与者对自己代表性研究工作的介绍和交流，互相学习启发，促进应用场景转换以解决实际临床问题。导师也会分享如何挑战临床问题展开自主创新的科研经历，并为博士毕业后的人生历练和职业生涯发展分享可能的建议。
Mentor: Assoc. Prof. Binjie Qin, Shanghai Jiao Tong University, China
导师: 上海交通大学秦斌杰副教授
Binjie Qin received his M.Sc. and
Ph.D. degrees from the Nanjing
University of Science and Technology,
Nanjing, and Shanghai Jiao Tong
University, Shanghai, China, in 1999 and
2002, respectively. He was a Lecturer
and an Associate Professor with the
School of Life Sciences and
Biotechnology, Shanghai Jiao Tong
University. From 2012 to 2013, He was a
Visiting Professor with the Department
of Computer Science, University College
London, U.K. He is currently an
Associate Professor with the School of
Biomedical Engineering, Shanghai Jiao
Tong University. His current research
interests include biomedical imaging,
image processing, machine learning,
computer vision, and biomedical
instrumentation. He has served a
reviewer for more than thirty journals
including IEEE Transactions on Image
Processing, IEEE Transactions on Neural
Networks and Learning Systems, Medical
Image Analysis, Pattern Recognition,
IEEE Transactions on Cybernetics,
IEEE/CAA Journal of Automatica Sinica,
Bioinformatics, IEEE Transactions on
Instrumentation and Measurement, IEEE
Transactions on Ultrasonics,
Ferroelectrics, and Frequency Control,
IEEE Signal Processing Letters, Physics
in Medicine and Biology. He is a leading
guest editor of “Cerebral vessel
extraction: from image acquisition to
machine learning” in Frontiers in
Neuroscience 2021-2022. He was awarded
as an outstanding reviewer of Pattern
Recognition 2018 and Journal of Shanghai
Jiaotong University 2020, 2021. His
group has developed several imaging
systems for image guided ENT surgery and
small animal fluorescence imaging, which
have preclinical and clinical
applications in some laboratories and
hospitals. Prof. Qin and his group have
published more than 60 papers with over
30 papers in SCI/EI indexed journals
including IEEE Transactions on Image
Processing, Pattern Recognition, Neural
Networks, Applied Soft Computing, IEEE
Transactions on Instrumentation and
Measurement, Physics in Medicine and
Biology, IEEE Signal Processing Letters.
秦斌杰，副教授，硕士生导师。2002年获上海交通大学工学博士学位。2002年至2004年在上海交通大学生物医学工程系任讲师，2004年至2011年任副教授。2012.08-2013.08期间任伦敦大学学院计算机系访问教授。2014.05-2015.05期间任上海交通大学科学技术发展研究院院长助理。2011年至今任上海交通大学生物医学工程学院副教授。任IEEE
Transactions on Image Processing, IEEE
Transactions on Neural Networks and
Learning Systems, Medical Image
Analysis, Pattern Recognition, IEEE
Transactions on Cybernetics, IEEE/CAA
Journal of Automatica Sinica,
Bioinformatics, IEEE Transactions on
Instrumentation and Measurement, IEEE
Transactions on Ultrasonics,
Ferroelectrics, and Frequency Control,
IEEE Signal Processing Letters, Physics
in Medicine and
Biology等三十多家国际期刊的审稿人，2021年Frontiers in
Neuroscience专刊"Cerebral vessel
extraction: from image acquisition to
machine
learning"客座编辑，2021和2020年度《上海交通大学学报》有突出贡献审稿专家，2018年度Pattern
Recognition杂志杰出审稿人，国家自然科学基金面上项目，教育部博士点基金项目，浙江省、黑龙江省、河北省、陕西省、广西省自然科学基金项目和省市高层次创业人才引进项目评审专家。
他主要从事生物医学成像和图像视频处理、计算机视觉和机器学习、信号处理和生命科学仪器、以及科技分类评价和创新机制等方面的研发活动。主持多项国家自然科学基金面上项目、上海市及企业合作项目，他的团队自主研发了已用于临床和科研的计算机辅助手术导航系统、生物发光和荧光成像系统等。