CCF-TF 智能媒体计算国际研讨会

2022 年 5 月 23 日 CCF多媒体专委会

Overview

CCF-TF International Symposium on Intelligent Media Computing is co-hosted by China Computer Federation (CCF) and Temasek Foundation (TF), and is jointly organized by CCF Multimedia Technical Committee and Nanyang Technological University, Singapore. The symposium comprises a series of monthly research seminars and will be held online. In each seminar, well-known researchers from China, Singapore and USA will introduce the frontier advances in various aspects of artificial intelligence, including but not limited to future intelligent media, robotics, multimedia analysis and retrieval, media coding and transmission, intelligent media and health, artificial intelligence in healthcare, FinTech, etc. The first phase is Future Media Computing.

CCF-TF智能媒体计算国际研讨会是由中国计算机学会（CCF）和淡马锡基金会（TF）联合主办，CCF多媒体专委会和新加坡南洋理工大学共同承办的系列性学术活动。会议拟设7个专题分论坛，以线上的形式每月举办一次。每个专题包含三个特邀报告，邀请来自中国、新加坡、美国等国家的知名专家学者分享人工智能领域的前沿进展。会议议题涵盖未来智能媒体、机器人、多媒体检索与分析、信息编码与传输、智能媒体与健康、智慧医疗、金融科技等。第一期为未来媒体计算。

Schedule
Time	Speaker	Topics	Host
9:00-9:10	Wenwu Zhu Weisi Lin	Opening and Introduction	Shuqiang Jiang
9:10-10:10	Chua Tat-Seng	Challenges in Multimodal Conversational Search and Recommendation
10:10-11:10	Wenwu Zhu	Automated Machine Learning on Graphs
11:10-12:10	Chia-Wen Lin	Making the Invisible Visible: Toward High-Quality Deep THz Computational Imaging
12:10-12:15		Closing

*All times are at May 27 (Friday), 2022, China Standard Time (CST), UTC +8

Invited Speakers

Prof. Chua Tat-Seng

Prof. Chua is the KITHCT Chair Professor at the School of Computing, National University of Singapore (NUS). He is also the Distinguished Visiting Professor of Tsinghua University and the Visiting Pao Yue-Kong Chair Professor of Zhejiang University. Dr. Chua was the Founding Dean of the School of Computing from 1998-2000. His main research interests include unstructured data analytics, video analytics, conversational search and recommendation, and robust and trustable AI. Dr. Chua is the co-Director of NExT, a joint research Center between NUS and Tsinghua, and Sea-NExT, a joint Lab between Sea Group and NExT. Dr. Chua is the recipient of the 2015 ACM SIGMM Achievements Award for the Outstanding Technical Contributions to Multimedia Computing, Communications and Applications. He is the Chair of steering committee of Multimedia Modeling (MMM) conference series, and ACM International Conference on Multimedia Retrieval (ICMR) (2015-2018). He was the General Co-Chair of ACM Multimedia 2005, ACM CIVR (now ACM ICMR) 2005, ACM SIGIR 2008, ACM Web Science 2015, ACM MM-Asia 2020, and the upcoming ACM conferences on WSDM 2023 and TheWebConf 2024. He serves in the editorial boards of three international journals. Dr. Chua is the co-Founder of two technology startup companies in Singapore. He holds a PhD from the University of Leeds, UK.

Title: Challenges in Multimodal Conversational Search and Recommendation

Abstract: Information search has been evolving from mostly unidirectional and text-based to interactive and multimodal. Recently, there is also a growing interest in all matters conversational. Multimodal conversation offers users a natural way to query the system by combining text/speech, images/videos and possibly gesture. It also helps to tackle the basic asymmetric problems by injecting conversation to help resolve the ambiguities in search and recommendation. However, the evolution from traditional IR to multimodal conversational search and recommendation (MCSR) faces many challenges. The first set of challenges touches on the basic MCSR models, including how to integrate task-oriented and open domain models, how to model multimodal context and history, and how to integrate domain knowledge and user models. The second set of challenges involves basic interactivity issues, including how to naturally converse using text and visual modalities, how to incorporate intervention strategy into search and browsing; and how to perform interactive IR, QA and recommendation. The third set of challenges looks more into the future on how to build dialogue simulator, and how to make MCSR systems extendable and active by allowing the system and users to co-evolve and becoming more intelligent together. This talk presents current research with pointers towards future research.

Prof. Wenwu Zhu

Wenwu Zhu is currently a Professor of Computer Science Department of Tsinghua University and Vice Dean of National Research Center on Information Science and Technology. Prior to his current post, he was a Senior Researcher and Research Manager at Microsoft Research Asia. He was the Chief Scientist and Director at Intel Research China from 2004 to 2008. He worked at Bell Labs New Jersey as a Member of Technical Staff during 1996-1999. He has been serving as the chair of the steering committee for IEEE T-MM since January 1, 2020. He served as the Editor-in-Chief for the IEEE Transactions on Multimedia from 2017 to 2019, and Vice EiC for IEEE Transactions on Circuits and Systems for Video Technology from 2020-2021. He served as co-Chair for ACM MM 2018 and co-Chair for ACM CIKM 2019. His current research interests are in the areas of multimodal big data and intelligence, and multimedia networking. He received 10 Best Paper Awards. He is a member of Academia Europaea, an IEEE Fellow, AAAS Fellow, and SPIE Fellow.

Title: Automated Machine Learning on Graphs

Abstract: Automated machine learning (AutoML) on graphs, which combines the strength of graph machine learning and AutoML, is gaining attentions from the research community. This talk will first overview graph machine learning and AutoML on graphs. Then, recent advances, including efficient neural architecture search for self-attention representation, hyper-parameter optimization on large-scale graphs, and increasing explainability in AutoML on graphs, will be discussed. We will also introduce AutoGL, the first dedicated framework and open-source library for AutoML on graphs, which is expected to facilitate the research and application in the community. Last but not least, we discuss multimedia applications of automated graph machine learning and share our insights on future research directions with the audience.

Prof. Chia-Wen Lin

Prof. Chia-Wen Lin is currently a Professor with the Department of Electrical Engineering, National Tsing Hua University (NTHU), Taiwan. He also serves as Deputy Director of the AI Research Center of NTHU. His research interests include image/video processing, computer vision, and video networking.

Dr. Lin is an IEEE Fellow, and has been serving on IEEE Circuits and Systems Society (CASS) Fellow Evaluating Committee since 2021. He serves as IEEE CASS BoG member-at-Large during 2022-2024. He was Steering Committee Chair of IEEE ICME (2020-2021), IEEE CASS Distinguished Lecturer (2018-2019), and President of the Chinese Image Processing and Pattern Recognition (IPPR) Association, Taiwan (2019-2020). He has served as Associate Editor of IEEE Transactions on Image Processing, IEEE Transactions on Multimedia, IEEE Transactions on Circuits and Systems for Video Technology, and IEEE Multimedia. He also served as a Steering Committee member of the IEEE Transactions on Multimedia. He was Chair of the Multimedia Systems and Applications Technical Committee of the IEEE CASS. He has served as TPC Chair of IEEE ICME in 2010 and IEEE ICIP in 2019, and the Conference Chair of IEEE VCIP in 2018. His papers won the Best Paper Award of IEEE VCIP 2015, and the Young Investigator Award of VCIP 2005.

Title: Making the Invisible Visible: Toward High-Quality Deep THz Computational Imaging

Abstract: Terahertz (THz) computational imaging has recently attracted significant attention thanks to its non-invasive, non-destructive, non-ionizing, material-classification, and ultra-fast nature for 3D object exploration and inspection. However, its strong water absorption nature and low noise tolerance lead to undesired blurs and distortions of reconstructed THz images. The performances of existing methods are highly constrained by the diffraction-limited THz signals. In this talk, we will introduce the characteristics of THz imaging and its applications. We will also show how to break the limitations of THz imaging with the aid of complementary information between the THz amplitude and phase images sampled at prominent frequencies (i.e., the water absorption profile of THz signal) for THz image restoration. To this end, we propose a novel physics-guided deep neural network design, namely Subspace-Attention-guided Restoration Network (SARNet), that fuses such multi-spectral features of THz images for effective restoration. Furthermore, we experimentally construct an ultra-fast THz time-domain spectroscopy system covering a broad frequency range from 0.1 THz to 4 THz for building up temporal/spectral/spatial/phase/material THz database of hidden 3D objects.

Organizers