Keynote Speakers 按姓氏拼音排列

Speaker

高新波

西安电子科技大学

Invited Speakers 按姓氏拼音排列

Speaker

韩军伟

西北工业大学

Speaker

纪荣嵘

厦门大学

Speaker

Dahua Lin

Chinese University of Hong Kong

Speaker

Hongdong Li

澳大利亚国立大学

Speaker

林宙辰

北京大学

Speaker

欧阳万里

香港中文大学

Speaker

吴飞

浙江大学

Speaker

吴建鑫

南京大学

Speaker

杨铭

地平线机器人联合创始人兼软件副总裁

Speaker

Kevin Zhou

Siemens Healthcare Technology

Speaker

朱军

清华大学

讲者介绍

  高新波 个人主页 西安电子科技大学

报告题目:异质图像合成与识别

报告摘要:本次报告将以异质人脸图像合成和识别为例探讨人机混合智能和跨媒体智能的相关问题和思考。报告将系统总结我们团队近十年来在异质人脸图像识别,即素描画像和灰度图像之间的跨媒体识别工作,包括基于异质图像合成的方法和直接跨媒体识别方法,基于概率图模型的方法和基于深度学习的方法等。这些方法可以推广到其他异质图像的变换和识别中,如近红外与可见光图像,低分辨与高分辨图像,甚至CT和MR图像中,在在刑侦破案、网络追逃、动漫设计以及医学诊断等领域具有广泛的应用前景。

讲者信息:高新波,博士,教授,西安电子科技大学模式识别与智能系统学科带头人,综合业务网理论及关键技术国家重点实验室主任,国家万人计划科技创新领军人才,新世纪百千万人才工程国家级人选,国家杰出青年科学基金获得者,教育部长江学者特聘教授,科技部重点领域创新团队负责人、教育部创新团队负责人。IET Fellow、CIE Fellow、IEEE高级会员、中国图象图形学学会常务理事、中国计算机学会理事、中国指挥与控制学会富媒体指挥专委会常务委员、中国电子学会青年科学家俱乐部副主席。主要从事计算机视觉机器学习等领域的研究和教学工作,获国家自然科学二等奖1项、省部级科学技术一等奖3项。

  韩军伟 个人主页 西北工业大学

报告题目:脑神经媒体组学

报告摘要:人脑是图像/视频内容的最终判定者,随着脑科学技术的飞速发展,可以利用非侵入的磁共振功能成像手段获取大脑在观看多媒体时的反应,这种反应包含大脑的语义层理解信息。“脑神经媒体组学”是一个新的研究方向,利用机器学习理论为手段,实现大脑反应信息对多媒体视听觉特征的指导、优化和融合,达到计算机对于多媒体内容实现接近人脑认知的目的。同时,此研究也探索大脑在多媒体刺激下的工作机制。本报告将汇报“脑神经媒体组学”研究中的一些关键技术及最新进展。

讲者信息:韩军伟,西北工业大学教授,自动化学院副院长,信息融合技术教育部重点实验室副主任,国家优秀青年科学基金获得者,欧盟玛丽居里学者,陕西省重点科技创新团队负责人。主要研究方向是多媒体信息处理和脑成像分析。已在领域顶级期刊如:Proceedings of the IEEE,IEEE TPAMI, IJCV, NeuroImage, Cerebral Cortex等发表学术论文60余篇,在领域顶级的国际会议如:CVPR,ICCV,MICCAI,IPMI, IJCAI等发表学术论文30余篇。ESI高被引论文12篇,ESI热点论文5篇。获得国际会议ACM Multimedia 2010,MICCAI 2011和ICME 2016最佳学生论文奖提名。获得教育部自然科学二等奖(排名第一)等省部级科技奖励3项。担任IEEE TNNLS、IEEE THMS等6个国际期刊编委,担任ICPR, ACCV等多个国际会议的Area Chair.

  纪荣嵘 个人主页 厦门大学

报告题目:紧致化视觉大数据分析系统

报告摘要:报告主要探索视觉大数据搜索识别系统中的紧凑性问题,将覆盖纪荣嵘教授研究组近两年来在面向视觉终端应用的视觉特征紧凑表示和深度网络压缩中所做的一些工作与成果。在视觉特征紧凑表示方面,将介绍通过引入大规模无监督排序信息,学习排序敏感的哈希码,以保持原始高维特征空间中的检索信息。在深度网络压缩方面,将介绍面向特定任务(人脸和视觉场景解析)的深度网络级联压缩模型(串行低秩矩阵分解技术)与加速模型(结构化稀疏约束剪枝技术)。报告并将介绍上述研究在腾讯\滴滴\华为等视觉产品中的实际应用。

讲者信息:纪荣嵘,福建省“闽江学者”特聘教授,厦门大学教授、博士生导师、2014年获国家优青,2016年获国家万人计划青年拔尖。主要研究方向为计算机视觉与多媒体技术。相关工作发表于SCI源期刊论文90余篇,包括ACM汇刊与IEEE汇刊近50篇、CCF A类国际会议长文40余篇。论文的Google Scholar引用次数近5000次,SCI引用1600余次,H-因子为33,12篇论文入选ESI高被引/热点论文;近年来主持国家自然科学基金联合重点项目、军委科技委战略前沿专项,国家重点研发计划课题/子课题等;获2007年微软学者奖、2011年ACM Multimedia最佳论文奖、2012年哈工大优秀博士论文、2015年省自然科学二等奖、2016年教育部技术发明一等奖。担任多个国际期刊的副编辑,VALSE 2017大会主席、ACM/IEEE高级会员。

  Dahua Lin 个人主页 Chinese University of Hong Kong

报告题目:Deep Understanding of Structures in the Visual World

报告摘要:It goes without saying that the success of deep learning is amazing. The rise of deep learning not only leads to a wave of breakthroughs in traditional AI areas, e.g. speech recognition and computer vision, but also opens up a number of possibilities that are unimaginable before — AI can now play chess games, perform cancer diagnosis, and even drive a car. Despite all such successful stories, the “intelligence” of most deep networks remain rather restrictive — they are essentially doing A to B regression, just that they are doing it particularly well. In the past two years, I worked with a group of talented students on a series of problems, with an aim to move beyond the aforementioned limitations and thus extend the power of deep models to more application domains. Many of our studies revolve around an important theme, namely, learning deep models from structured data. Particularly, we develop new modeling frameworks for high-resolution images, event photos, structured scenes, activity videos, movies, relational databases, etc. All such data, despite their different natures, have an important aspect in common, that is, they all contain structures, i.e. components related to each other. Analysis of their inherent structures not only gives us deeper insights into these domains, but also results in more effective models and training strategies (e.g. self-supervised training that does not rely on external supervision). In this talk, I will give a high-level review of our efforts and achievements, and share my thoughts and reflections on the underlying problems.

讲者信息:Dahua Lin is an Assistant Professor at the department of Information Engineering, the Chinese University of Hong Kong. He received the B.Eng. degree from the University of Science and Technology of China (USTC) in 2004, the M. Phil. degree from the Chinese University of Hong Kong (CUHK) in 2006, and the Ph.D. degree from Massachusetts Institute of Technology (MIT) in 2012. Prior to joining CUHK, he served as a Research Assistant Professor at Toyota Technological Institute at Chicago, from 2012 to 2014. His research interest covers computer vision, machine learning, and big data analytics. In recent years, he primarily focused on deep learning and its applications on high-level visual understanding, probabilistic inference, and big data analytics. He has published about sixty papers on top conferences and journals, e.g. ICCV, CVPR, ECCV, NIPS, and T-PAMI. He serves as an Area Chair of ECCV 2018. His seminal work on a new construction of Bayesian nonparametric models has won the best student paper award in NIPS in year 2010. He also received the outstanding reviewer award in ICCV 2009 and ICCV 2011. He has supervised or co-supervised the CUHK team in international competitions and won multiple awards in ImageNet 2016, ActivityNet 2016, and ActivityNet 2017.

  Hongdong Li 个人主页 澳大利亚国立大学

报告题目:Some Recent Work on Non-Rigid Shape Structure-From-Motion with a Monocular Perspective Camera: Sparse and Dense Solutions.

报告摘要:In this talk, I will describe some of our recent work on monocular perspective camera based reconstruction of the non-rigid 3D shape or an object or a complex scene. We aim to answer an open question in 3D vision: “is it possible to recover the 3D shape of a dynamic deformable object with a single moving camera?”. Traditional methods for dynamic 3D reconstruction often employ stereo-vision, or assume the scene (with deformable object) follows certain simple low-order linear model. Our new work removes such restrictions and shows that, under certain mild assumptions, monocular 3D reconstruction of a dynamic shape scene is possible. I will explain two approaches, one is for the recovery of 3D dynamic human pose using structured movement, and the other is a dense surface reconstruction method for complex dynamic scene. Both methods achieved superior performance on standard benchmarks datasets.

讲者信息:Dr. Hongdong Li is an Associate Professor/Reader with the Computer Vision Group of ANU (Australian National University) and Chief Investigator for Australian Centre for Robotic Vision (ACRV). His research interests include 3D computer vision, SFM/SLAM for robot navigation and autonomous vehicles, as well as the application of mathematical optimization in geometric vision. He graduated from Zhejiang University, and taught at the same university before joined the ANU as a research fellow since 2004. During 2009-2010 he was a senior researcher with NICTA (Canberra Labs) working on the “Australia Bionic Eyes” project. He was a visiting professor with Carnegie Mellon University in 2017. He served as the Area Chair for CVPR, ICCV, ECCV, BMVC and 3DV in the past; Associate Editor for IEEE Transactions on PAMI (T-PAMI); Program Co-Chair for ACCV 2018. Jointly with students and co-workers he won a number of prestigious awards in computer vision, which include the CVPR Best Paper Award and Marr Prize-Honorable Mention.

  林宙辰 个人主页 北京大学

报告题目:A Brief Overview of Practical Optimization Algorithms in the Context of Relaxation

报告摘要:Optimization is an indispensable part of machine learning. There have been various optimization algorithms, typically introduced independently in textbooks and scatter across vast materials, making the beginners hard to have a global picture. In this talk, by explaining how to relax some aspects of optimization procedures I will briefly introduce some practical optimization algorithms in a systematic way.

讲者信息:Zhouchen LIN received the Ph.D. degree in applied mathematics from Peking University in 2000. He is currently a Professor with the Key Laboratory of Machine Perception, School of Electronics Engineering and Computer Science, Peking University. His research interests include computer vision, image processing, machine learning, pattern recognition, and numerical optimization. He is an area chair of ACCV 2009/2018, CVPR 2014/2016, ICCV 2015, and NIPS 2015, and senior program committee of AAAI 2016/2017/2018 and IJCAI 2016/2018. He is an Associate Editor of the IEEE Transactions on Pattern Analysis And Machine Intelligence and the International Journal of Computer Vision. He is an IAPR/IEEE fellow.

  欧阳万里 个人主页 香港中文大学

报告题目:Exploring Deep Structures in Computer Vision tasks

报告摘要:Structure in data provide rich information that helps to reduce the complexity and improves the effectiveness of a model. In this talk, an introduction will be given on the recent progress in using deep learning as a tool for modeling the structure in visual data. We show that observation in our problem are useful in modeling the structure of deep model and help to improve the effectiveness of deep models for many vision problems.

讲者信息:Wanli Ouyang received the PhD degree in the Department of Electronic Engineering, The Chinese University of Hong Kong. He is now a senior lecturer at the University of Sydney. His research interests include image processing, computer vision and pattern recognition. He is the first author of 7 papers on TPAMI and IJCV, and has published around 40 papers on top tier conferences like CVPR, ICCV and NIPS. ImageNet Large Scale Visual Recognition Challenge (ILSVRC) is one of the most important grand challenges in computer vision. The team led by him ranks No. 1 in the ILSVRC 2015 and ILSVRC 2016. He receives the best reviewer award of ICCV. He has been the reviewer of many top journals and conferences such as IEEE TPAMI, TIP, IJCV, SIGGRAPH, CVPR, and ICCV. He is a senior member of the IEEE.

  吴飞 个人主页 浙江大学

报告题目:Memory-augmented learning

报告摘要:Neural networks with a memory capacity provide a promising approach to media understanding (e.g., Q-A and visual classification). In this talk, I will present how to utilize the information in external memory to boost media understanding. In general, the relevant information (e.g., knowledge instance and exemplar data) w.r.t the input data is sparked from external memory in the manner of memory-augmented learning. Memory-augmented learning is an appropriate method to integrate data-driven learning, knowledge-guided inference and experience exploration.

讲者信息:Fei Wu is a professor at the college of computer science, Zhejiang University. From October, 2009 to August 2010, Fei Wu was a visiting scholar at Prof. Bin Yu's group, University of California, Berkeley. Currently, he is the vice-dean of college of Computer Science, and the director of Institute of Artificial Intelligence of Zhejiang University. His research interests mainly include Artificial Intelligence, cross-media computing, and multimedia retrieval. He has won various honors such as the Award of National Science Fund for Distinguished Young Scholars of China (2016).

  吴建鑫 个人主页 南京大学

报告题目:深度学习实践:庖丁解牛与盲人摸象

报告摘要:深度学习是目前计算机视觉与机器学习领域最热门、也是在很多实际问题中实践效果最好的方法。然而,深度学习,尤其是卷积神经网络CNN的机理目前尚不明确。本次报告将介绍我们研究组在CNN深度学习方向上两个方面的实践:庖丁解牛与盲人摸象。庖丁解牛即将CNN的各个构成模块分别探索,发现其优缺点并加以改进,从而对CNN的各个模块形成深入的理解。盲人摸象即对在ImageNet上学习到的CNN预训练模型能起到什么样的作用加以研究,在CNN整体机理尚不清楚的前提下,对预训练模型在各个视觉问题中的无监督应用加以研究。

讲者信息:南京大学教授,Minieye首席科学家(minieye.cc)。研究兴趣为计算机视觉与机器学习,尤其是资源(计算、存储、能源、数据与标注)受限情况下的深度学习。曾获中组部青年千人和基金委优秀青年科学基金资助,曾任ICCV、CVPR等领域主席。

  杨铭 地平线机器人联合创始人兼软件副总裁

报告题目:

报告摘要:

讲者信息:杨铭博士,地平线(Horizon Robotics)联合创始人 & 软件副总裁,Facebook 人工智能研究院创始成员之一。杨铭曾任 NEC 美国研究院高级研究员,专注于计算机视觉和机器学习领域研究,包括物体跟踪、人脸识别、海量图片检索、及多媒体内容分析。他在 Facebook 工作期间负责的深度学习研发项目 DeepFace 在业界产生重大影响,被多家媒体广泛报道,包括 Science Magazine、MIT Tech Review、Forbes 等。他领导 NEC-UIUC 团队参加 TRECVID08/09 视频监控事件检测评测,获得最佳成绩;参与 NEC 团队 ImageNet2010 大规模图像分类挑战,获得第一名。申请获得美国专利14项。杨铭毕业于清华大学电子工程系并获得工学学士和硕士学位,于美国西北大学电气工程与计算机科学系获得博士学位。他在顶级国际会议 CVPR/ICCV 发表论文20余篇,在顶级国际期刊 T-PAMI 上发表8篇论文,被引用超过6200次;多次担任 CVPR/ICCV/NIPS/ACMMM 等顶级国际会议程序委员会成员,T-PAMI/IJCV/T-IP 等顶级国际期刊审稿人。

  Kevin Zhou 个人主页 Principal Key Expert of Image Analysis at Siemens Healthcare Technology

报告题目:Deep learning and beyond: medical image recognition, segmentation, parsing

报告摘要:The "Machine learning + Knolwedge" approaches, which combine meachine learning with domain knowledge, enable us to achieve start-of-the-art performances for many tasks of medical image recognition, segmentation and parsing. In this talk, we first present real success stories of such approaches. Then, we proceed to elaborate deep learning, a special, mighty type of machine learning method, and review its recent advances. We conclude with several latest "DL & Beyond" works.

讲者信息:Dr. S. Kevin Zhou is currently a Principal Key Expert of Image Analysis at Siemens Healthcare Technology, dedicated to researching and developing innovative solutions for medical and industrial imaging products. His research interests lie in computer vision and machine learning and their applications to medical image recognition and parsing, face recognition and modeling, etc. Dr. Zhou has published over 150 book chapters and peer-reviewed journal and conference papers, has registered over 250 patents and inventions, has written two research monographs, and has edited three books. His two most recent books are entitled "Medical Image Recognition, Segmenation and Parsing: Machine Learning and Multiple Object Approaches, SK Zhou (Ed.)" and "Deep Learning for Medical Image Analysis, SK Zhou, H Greenspan, DG Shen (Eds.)." He has won multiple awards honoring his publications, patents and products, including Thomas Alva Edison Patent Award (2013), R&D 100 Award or Oscar of Invention (2014), Siemens Inventor of the Year (2014), and UMD ECE Distinguished Aluminum Award (2017). He has been an associate editor for IEEE Trans Medical Imaging and Medical Image Analysis journals, an area chair for CVPR and MICCAI, a co-Editor-in Chief for WeChat public journal The Vision Seeker, and elected as a fellow of American Institute of Biological and Medical Engineering (AIMBE).

  朱军 个人主页 清华大学

报告题目:

报告摘要:深度生成模型是一类灵活的从复杂数据中提取隐含结构并且进行“从上到下”生成样本的方法,广泛用于无监督学习、半监督学习等任务。该报告将介绍最近的一些前沿进展,包括用于半监督学习的模型和算法,以及支持快速编程实现的珠算(ZhuSuan)编程库。

讲者信息:朱军,清华大学长聘副教授、卡内基梅隆大学兼职教授、智能技术与系统国家重点实验室副主任。2001到2009年获清华大学计算机学士和博士学位,之后在卡内基梅隆大学做博士后,2011年回清华任教。主要从事人工智能基础理论、高效算法及相关应用研究,在国际重要期刊与会议发表学术论文近百篇。受邀担任人工智能顶级杂志IEEE TPAMI和AI的编委、《自动化学报》编委,担任机器学习国际大会ICML2014地区联合主席, ICML (2014-2018)、NIPS (2013, 2015)、UAI (2014-2017)、IJCAI(2015,2017)、AAAI(2016-2018)等国际会议的领域主席,中国计算机学会(CCF)学术工委主任助理。获CCF优秀博士论文奖、CCF自然科学一等奖、CCF青年科学家奖、国家优秀青年基金、北京市优秀青年人才奖、清华大学优秀班主任一等奖等,入选国家“万人计划”青年拔尖人才、IEEE Intelligent Systems杂志评选的“AI’s 10 to Watch”及清华大学221基础研究人才计划。指导的学生获NIPS 2017国际人工智能对抗攻防竞赛全部三个任务的冠军。