James She_Seminar.ppt
Ming Cheung_Seminar.ppt
Allan Jie_Seminar.ppt
香港科技大学助理教授Dr. James She和他的两位博士生，将应邀于10月21日（下周二）上午10：00～11：50在电信系会议室（南一楼中302室）做三个学术报告，特此通知。欢迎各位师生参加。
Professor James She
Director, HKUST-NIE Social Media Lab.,
Assistant Professor, Electronic & Computer Engineering,
Hong Kong University of Science & Technology, Hong Kong
Title: From Mobile Social Media to Cyber-physical Social Media
Abstract:
Due to the technologies of smart mobile devices, mobile apps, wireless communication/networking, we are witnessing how social media and various sticky applications have influenced user behaviors to a point that social media is no longer just for causal social networking and content sharing purposes. Mobile social media today has redefined the daily lifestyles of users, and even the strategies of business advertising and marketing. With possible advances in wearable computing and sensors, Internet-of-things, and pervasive displays, the emerging momentum of cyber-physical systems that consider the physical conditions/constraints of a system, users and the operating environment, will definitely evolve social media to another level of impacts through a new form of cyber-physical social media that contains rich information about social interactions more than just between users. In this talk, we will explore such emerging form of cyber-physical social media may unleash exciting applications like those in a sci-fi movie by illustrating some recent results from our Lab., whereas discussing new challenges and opportunities to explore novel techniques of data analytics, system designs and interactive media technologies.
Speaker's bio:
James She is an assistant professor in the Department of Electronic and Computer Engineering at the Hong Kong University of Science and Technology (HKUST), and a visiting research fellow at the University of Cambridge. He is also the founding director of Asia's first social media lab, HKUST-NIE Social Media Lab, and spearheads multidisciplinary research and innovation in cyber-physical social media systems, viral media analytics and mobile media broadcast systems. He is actively serving several international conferences and journals, such as currently as the Program Chair in ASE/ACM SocialCom2014, TPC Chair in CPSCom2014, General Chair in IEEE PhoneCom2014 and an Editor of a special issue in 2014 for ACM Transaction on Multimedia Computing, Communication and Applications. Celebrated as a thought leader in new media and emerging cyber-physical societies, James is also a member of the World Economic Forums Global Agenda Council (Social Media) and advisor for two social media companies, and joins other government and business leaders to develop solutions for key social media issues on the global and industrial agendas.
http://smedia.ust.hk/james/
Director, HKUST-NIE Social Media Lab.,
Assistant Professor, Electronic & Computer Engineering,
Hong Kong University of Science & Technology, Hong Kong
Ming Cheung
PhD candidate, HKUST-NIE Social Media Lab
Title: A Reality Check on a P2P-based IPTV System - from the Operator’s Perspective
Abstract:
This paper conducts a summarized reality check of a P2P-based IPTV system from the operator’s perspective (NextTV) through the analysis of large-scale operational data. NextTV is an IPTV system by a leading Asia media company based in Taiwan - NextMedia, in which P2P delivery mechanism is adopted to deal with system and network scalability issues for popular videos. This paper contributes by revealing 1) the relationship between the user properties and video popularity and 2) how effective the P2P mechanism is in the IPTV system for popular videos with different user properties. The results demonstrate a successful showcase of using the P2P delivery mechanism for IPTV services by analyzing the real operational data of all users. The approach is different from many previous works which has used simulations, test-beds and traffic measurements of an incomplete collection of users. The results potentially helps the design of the next generation of the P2P delivery mechanism for IPTV services.
Speaker's bio:
Ming Cheung was born in Hong Kong. He received his B.Eng. and M.Phil in Electronic and Computer Engineering at Hong Kong University of Science and Technology (HKUST) in 2010 and 2012 respectively. He joined the HKUST-NIE Social Media Lab in 2012 as a research assistant, and currently is a Ph.D. candidate at HKUST. His research interests include social media analytics, information diffusions and user behavior predictions.
http://smedia.ust.hk/ming
PhD candidate, HKUST-NIE Social Media Lab.,
Department of Electronic & Computer Engineering,
Hong Kong University of Science & Technology, Hong Kong
Allan Jie
PhD Student, HKUST-NIE Social Media Lab
Title: Bag-of-Features Tagging Approach for a Better Recommendation with Social Big Data
Abstract:
The interests of users are always important for personalized content recommendations on friendships, events and media content from the social big data. However, those interests may not be specified, which makes the recommendations challenging. One of the possible solutions is to analyze the user’s interests from the shared content, especially images with manually annotated tags. They are shared on online social networks such as Flickr and Instagram. However, the accuracy of the recommendation is greatly affected by the accuracy of the tag, which is not always reliable. This paper demonstrates how a bag-of-features (BoF)-based tagging approach can help to improve the accuracy of recommendations using an unsupervised algorithm. A set of auxiliary tags is used to represent user interests and, hence, the recommendation. The approach is evaluated with over 500 user and 200k images from Flickr. It is proven that by BoF tagging (BoFT), friendship recommendation is possible without friendship/tag information and the recall and the precision rate are improved by about 50% over using user tags.
Speaker's bio:
Allan Jie is a first-year PhD student in the Department of Electronic and Computer Engineering at the Hong Kong University of Science and Technology (HKUST). He got his bachelor degree from University of Electronic Science and Technology of China (UESTC) with the first honor. Before join HKUST, he was a research assistant at Singapore University of Technology and Design (SUTD) and focusing on natural language processing. Currently, his research interest includes social network and big data analysis.
PhD Student, HKUST-NIE Social Media Lab.,
Department of Electronic & Computer Engineering,
Hong Kong University of Science & Technology, Hong Kong
