图像图形中国行是中国图象图形学会的一个品牌学术活动。为促进前沿学术交流，于2024年12月18日在华东师范大学举办CSIG-图像图形中国行学术活动。本次会议邀请加拿大Concordia大学Ching Y Suen教授（加拿大皇家科学院院士、模式识别领域最高奖FuSK奖获得者）、南昌大学刘丽副教授、上海人工智能实验室陈昕苑研究员作学术报告，围绕“图像与视频的识别与生成”进行成果分享和前沿技术研讨，以促进大模型背景下的相关前沿技术研究和人才培养。由中国图象图形学学会理事、华东师范大学通信与电子工程学院院长吕岳教授和CSIG文档图像分析与识别专委会常务委员、上海合合信息科技股份有限公司总监郭丰俊共同担任执行主席。
时间：2024年12月18日下午13:30
地点：信息楼一楼魔方厅
主办单位：中国图象图形学学会
联合主办：上海市图像图形学学会
承办单位：
CSIG-文档图像分析与识别专委会
华东师范大学通信与电子工程学院
上海市多维度信息处理重点实验室
报告人：Ching Y Suen（加拿大皇家科学院院士，IEEE Fellow, IAPR Fellow）
报告题目: Pattern Recognition, AI, and Their Applications
Abstract: This talk is about (a) Pattern Recognition, the backbone of Artificial Intelligence, ways of recognizing different types of patterns and visible objects and coins using image processing and machine learning methodologies, and (b) AI - Artificial Intelligence, a bit of history, theory, and various applications. In this talk, we present their theory and applications and several image processing methodologies to recognize handwriting and its application in cell phone communication, to measure facial beauty, and to detect fake coins automatically. This system consists of feature measurement, 2D and 3D analysis, fuzzy set analysis, AI and deep learning techniques. For validation, large quantities of samples have been tested, and a near 100% accuracy has been achieved. Numerous examples will be demonstrated during this talk.
Biography: Dr. Ching Suen is the Honorary Chair of AI and Pattern Recognition of Concordia University. He is also the Founder and Co-Director of the world renowned CENPARMI (Centre for Pattern Recognition and Machine Intelligence). He Received an M.Sc. degree from the University of Hong Kong and a Ph.D. from UBC. He is specialized in the recognition of printed and handwritten characters, document analysis, analysis of facial beauty, and the detection of fake coins. He has been the Principal Investigator or Consultant of 30 industrial projects. Dr. Suen has published 8 conference proceedings, 16 books and more than 560 papers, and many of them have been widely cited while the ideas in others have been applied in practical environments involving character recognition, thinning methodologies, font analysis and multiple classifiers. He is the recipient of numerous awards, including IAPR 2020 King-Sun Fu Prize (highest honour in the field of Pattern Recognition given to only one person every two years), Elsevier Pattern Recognition Journal Award of Excellence (2016), Gold Medal from the University of Bari (Italy 2012), the IAPR ICDAR Award (2005), the ITAC/NSERC national award ($50,000 in 1993), and numerous others. He is not only the founder of four conferences: ICDAR, IWFHR/ICFHR, ICPRAI, and VI, but has also organized many international conferences including ICPR, ICDAR, ICFHR, ICPRAI, ICCPOL, and as Honorary Chair of numerous international conferences. Prof. Suen has supervised 120 doctoral and master's students to completion, and guided/hosted 100 long-term visiting scientists and professors. He is a fellow of the IEEE (since 1986), IAPR (1994), and the Academy of Sciences of the Royal Society of Canada (1995). Currently, he is the Emeritus Editor-in-Chief of the journal of Pattern Recognition, an Adviser or Associate Editor of 5 other journals, and Editor of a new book series on Language Processing, Pattern Recognition, and Intelligent Systems. This year, he is the Honorary/General Chair of ICPRAI (Korea), HSI (Paris), ANNPR (Montreal), ICAIDL (Nanjing), and CEII (Singapore).
报告人：刘丽（南昌大学 副教授）
报告题目:基于组件级风格学习与结构感知引导的中国书法字体生成研究
报告摘要：中国书法字体生成是一个具有高度挑战性的研究领域，其复杂性主要源于汉字数量的庞大、笔画细节的精细以及字符结构的复杂性。此外，作为一种独特的视觉艺术形式，书法笔画展现出丰富多样的风格变化，进一步增加了生成任务的难度。本报告深入探讨了中国书法字体生成领域的最新研究进展，并提出了一种创新性的方法，基于组件级风格学习与结构感知引导策略，从局部与全局两个层面有效捕捉书法字体的复杂特性，为解决相关挑战提供了新的思路和技术支持。
报告人简介：刘丽，工学博士，南昌大学数学与计算机学院副教授，硕士生导师，南昌大学 “215人才工程” 赣江青年学者，从事模式识别与深度学习等领域的研究工作，相关研究成果在TIP，TIFS，PR，ESWA等多个国际著名学术期刊上发表。主持完成国家自然科学基金、江西省自然科学基金等项目，参与多个国家以及省部级科研项目。
报告人：陈昕苑（上海人工智能实验室 研究员）
报告题目: 基于扩散模型的大规模生成式视频生成模型
Abstract: As OpenAI introduces Sora, a generative text-to-video diffusion model, it opens the door to generation of high-definition videos at the minute level from text descriptions. This groundbreaking model not only showcases the vast potential of video generation but also captures the attention of researchers and enthusiasts alike. In this talk, we will delve into the evolutionary path of large-scale video generation models and explore key research milestones. We will then analyze the technical advancements and breakthrough effects achieved by the Sora model. However, while the success of Sora, there still exist limitations and bottlenecks in video generation. Concluding the talk, we will discuss the challenges faced in video generation and explore potential avenues for future breakthroughs.
Biography: Dr. Xinyuan Chen is currently a researcher at the Shanghai Artificial Intelligence Lab, collaborating closely with Prof. Yu Qiao. During 2020-2022, she did her post-doc research at East China Normal University, supervised by Prof. Yue Lu. In 2020, she completed her dual PhD from Shanghai Jiao Tong University and the University of Technology Sydney, under the supervision of Prof. Xiaokang Yang and Prof. Dacheng Tao. Her research interests lie in generative models, diffusion models, and generative adversarial networks. Currently, she focuses her work on image and video generation, large-scale video generation models, as well as controllable generation incorporating multi-modality and semantic conditions.
