In the research area of image and graphics, there emerge a considerable amount of new papers and young researchers each year. One important question that may attract wide attention from the researchers and especially those young talents is that, how to establish the research with personal trait, and make the voice heard and even outstanding. This forum has invited a few young scholars who have been working on the frontier of research in image and graphics. The speakers will not only share their recent research outcome, but also share their experience and thinking in the way of establishing their own research agenda and research branding.
IBM China Research Laboratory
Title: Recent AutoML work in IBM Research and the way from research to products
Abstract: In this lecture, Chao will present his work about AutoML and share his experience about doing research in the company. In the first part, he will give a brief introduction of considerable literature on AutoML which are based on genetic algorithms, random search, Bayesian optimization, reinforcement learning and continuous differentiable method. Then, considering most existing AutoML approaches required considerable overhead for model searching, he will present a so called transferable AutoML approach that leverages previously trained models to speed up the search process for new tasks and datasets. In the second half part, he will share his experience about how to bridge research work to products.
Biography: Xue Chao is a research scientist of IBM Research China. He mainly focuses on the optimization of machine learning/deep learning applications from hyper-parameter tuning to neural network search. He leads the project of performance optimization and tools for big data and deep learning on platform, which becomes a key component of IBM Watson Machine Learning Accelerator, and brings $10M extra revenue for the product team. Meanwhile, his research paper about AutoML—Transferable AutoML by Model Sharing over Grouped Datasets is accepted and published by the top conference of Computer Vision, CVPR. Also, at the top conference of Computer Science, PACT (The International Conference on Parallel Architecture and Compilation Techniques) 2016, he presented their accepted paper about big-data and machine learning at Haifa, Israel. He has ever taught AI courses at University of Chinese Academy of Sciences and Beijing Normal University, etc., and has finished more than 20 patents.
Title: Fun Research in Visual Computing
Abstract:Intelligent visual computing is a fundamental topic in image processing which has witnessed rapid progress in the last two decades. Due to various degradations in the image and video capturing, transmission and storage, image and video include many undesirable effects. The recovery of these degradations is ill-posed. With the wealth of statistic-based methods and learning-based methods, this problem can be unified into the cross-domain transfer, which cover more tasks.In this talk, I will discuss recent progresses of visual computing, and share some research experience in my group.
Biography:Jiaying Liu is currently an Associate Professor with the Institute of Computer Science and Technology, Peking University. She received the Ph.D. degree (Hons.) in computer science from Peking University, Beijing China, 2010. She has authored over 100 technical articles in refereed journals and proceedings, and holds 34 granted patents. Her current research interests include multimedia signal processing, compression, and computer vision.Dr. Liu is a Senior Member of IEEE and CCF. She was a Visiting Scholar with the University of Southern California, Los Angeles, from 2007 to 2008. She was a Visiting Researcher with the Microsoft Research Asia in 2015 supported by the Star Track Young Faculties Award. She has served as a member of the Multimedia Systems & Applications Technical Committee (MSA-TC) and the Education and Outreach Technical Committee (EO-TC) in IEEE Circuits and Systems Society, a member of the Image, Video, and Multimedia (IVM) Technical Committee in APSIPA. She has also served as the TPCChair of IEEE VCIP-2019/ACM ICMR-2021, the Publicity Chair of IEEE ICIP-2019/VCIP-2018/MIPR-2020, the Grand Challenge Chair of IEEE ICME-2019, and the Area Chair of ICCV-2019. She was the APSIPA Distinguished Lecturer (2016-2017).In addition, Dr. Liu also devotes herself to teaching. She has run MOOC Programming Courses via Coursera/edX/ChineseMOOCs, which have been enrolled by more than 60 thousand students. She is also the organizer of the first Chinese MOOC Specialization in Computer Science. She is the youngest recipient of Peking University Outstanding Teaching Award.
Beijing University of Technology
Title: Multimedia Technologies in Environmental Perception and Protection
Abstract: Facing the situation of tight resource constraints, serious environmental pollution and ecosystem degradation, adhering to the basic national policy of saving resources and protecting the environment, is related to the healthy life of the people and the expectation of happiness. However, there hasn’t been a certain gap between China’s environmental protection and national demand. The traditional environmental protection methods are difficult to deal with new pollution problems. During the last two years, the reporter has mainly focused on air quality monitoring. Relevant experience summed up a layman through unremitting thinking and efforts to enter the field of environmental protection information research. The related achievements break through the limitations of the traditional sensors for air quality monitoring in spatial and temporal domains, introducing the non-contacting multimedia-based measurements. The related work has been applied to atmospheric PM2.5 monitoring and exhaust black smoke monitoring, achieving amazing results.
Biography: Ke Gu is a professor and PhD supervisor at Beijing University of Technology. His researches mainly include image processing, quality assessment, environmental perception, and machine learning. He has published more than 40 IEEE Transactions papers. Dr. Gu is working as the editorial member of SPIC, DSP, IEEE Access and IET-IPR. He has won the IEEE T-MM best paper award in 2018, First Place of Natural Science Award of CIE in 2017, Extraordinary Ph.D. thesis award of CIE in 2016.
Shanghai Jiao Tong University
Title: Creating the research agenda from industry to academia
Abstract:In this talk, I will first give a brief introduction on graph matching, which is a combinatorial problem in nature. Then we will show a deep network based pipeline for addressing the graph matching problem via deep learning. The model involves learning of the graph node embedding, cross-graph affinity learning, and a Sinkhorn layer for solving the linear assignment task. We will also discuss some working paper on joint matching and link prediction among two or multiple graphs. In the end, some discussion will be given on the future work and outlook for connecting graph matching with machine learning. Moreover, I will briefly share my experience from industry to university, and how my research agenda evolves with this change, in order to build personal identity and sustainable research topics.
Biography:Dr. Junchi Yan is currently a Research Professor (PhD Advisor) with Department of Computer Science and Engineering and AI Institute of Shanghai Jiao Tong University. He is also the co-director for the prestigious SJTU ACM Class (in charge of AI direction). Before that, he was a Senior Research Staff Member with IBM Research – China where he started his career since April 2011, and once an adjunct professor with the School of Data Science, Fudan University. His research interests are machine learning, data mining and computer vision. He serves as an Associate Editor for IEEE ACCESS, (Managing) Guest Editor for IEEE Transactions on Neural Network and Learning Systems, Pattern Recognition Letters, Pattern Recognition, Vice Secretary of China CSIG-BVD Technical Committee, and on the executive board of ACM China Multimedia Chapter. He has published 40+ peer reviewed papers in top venues in AI and has filed 20+ US patents. He has once been with IBM Watson Research Center, Japan NII, and Tencent/JD AI lab as a visiting researcher. He won the Distinguished Young Scientist of Scientific Chinese for year 2018 and CCF Outstanding Doctoral Thesis.