Events for
Past Seminars and Events
September 06, 2019
  • Title: The Power of Data Analytics and AI Techniques in the Digital Sector

    Time: 05:30pm 

    Venue: Lecture Theatre A, Ground Floor, Chow Yei Ching Building, Main Campus, HKU

    Speaker(s): Mr Alan Chan

    Remark(s): 

    Speaker:
    Mr Alan Chan

    Executive Vice President Lazada (Alibaba's SE Asia Commerce Business)

    Date: September 6, 2019 (Friday)

    Time: 5:30 - 6:45pm (Refreshments will be served from 5:00pm)

    Venue: Lecture Theatre A, Ground Floor, Chow Yei Ching Building, Main Campus, HKU

     

    About the talk:

    In this talk, Mr Alan Chan will introduce how data analytics and AI techniques are used in the digital sector, and the changes that the industry is facing now and in the future. He will also share some tips on starting a career in data and analytics.

    About the speaker:

    With a background in strategy and analytics, and having led several organisations through their digital transformations, Alan is the Executive Vice President in Lazada (Alibaba’s South East Asia Commerce Business) and also part of the Alibaba Management Council. Alan joined Alibaba Group in 2016 and took on management roles in marketplace policy setting, data analytics and platform governance.

    Before joining Alibaba, he spent 13 years in consulting with Accenture and left in 2016 as the Managing Director and Partner of Accenture Digital team in China. Alan is passionate about leadership, digital marketplaces and data science.

    Outside of work, Alan engages actively in university collaborations and serves on the ex-officio board of a few start-ups in Asia. He received his Honors Degree in Economics and Statistics from the National University of Singapore, and is currently residing in Singapore.

    PDF

August 28, 2019
  • Title: Learning Neural Character Controllers from Motion Capture Data

    Time: 03:00pm 

    Venue: Room 328, Chow Yei Ching Building, The University of Hong Kong

    Speaker(s): Prof. Taku Komura

    Remark(s): 

    Prof. Taku Komura
    Institute of Perception, Action and Behaviour
    School of Informatics
    University of Edinburgh

     

    Date: August 28, 2019 Wednesday

    Time: 3:00pm

    Venue: Room 328 Chow Yei Ching Building The University of Hong Kong

     

    Abstract:

    I will cover our recent development of neural network-based character controllers. Using neural networks for character controllers significantly increases the scalability of the system - the controller can be trained with a large amount of motion capture data while the run-time memory can be kept low. As a result, such controllers are suitable for real-time applications such as computer games and virtual reality systems. The main challenge is in designing an architecture that can produce movements in production-quality and also manage a wide variation of motion classes. Our development covers lowlevel locomotion controllers for bipeds and quadrupeds, which allow the characters to walk, run, sidestep and climb over uneven terrain, as well as a high level character controller for humanoid characters to interact with objects and the environment, which allows the character to sit on chairs, open doors and carry objects. In the end of the talk, I will discuss about the open problems and future directions of character animation.

    About the speaker:

    Taku Komura is a Professor at the Institute of Perception, Action and Behaviour, School of Informatics, University of Edinburgh. As the leader of the Computer Graphics and Visualization Unit his research has focused on data-driven character animation, physically-based character animation, crowd simulation, cloth animation, anatomy-based modelling, and robotics. Recently, his main research interests have been the application of machine learning techniques for animation synthesis. He received the Royal Society Industry Fellowship (2014) and the Google AR/VR Research Award (2017).

    PDF

August 21, 2019
  • Title: Deep Composer: Music Generation Using Deep Neural Hashing

    Time: 02:00pm 

    Venue: Room 328, Chow Yei Ching Building, The University of Hong Kong

    Speaker(s): Prof. Kien A. Hua

    Remark(s): 

    Prof. Kien A. Hua
    Pegasus Professor and Director of the Data Systems Lab
    University of Central Florida

     

    Date: August 21, 2019 Wednesday

    Time: 2:00pm

    Venue: Room 328 Chow Yei Ching Building The University of Hong Kong

     

    Abstract:

    Recurrent neural networks have successfully generated pleasing melodies; however, they have struggled to create a full piece that has structure, theme, and originality. To overcome this limitation, we discuss a music retrieval approach for music generation. Composability, instead of the usual similarity, is used as the metric for retrieval. The musical segments (tiny building blocks each with only 16 music notes) in the database are encoded using a deep hashing method to facilitate the composability retrieval. Music composition is performed by using the current segment as a query to retrieve the next composable segment from the database until the song is complete. This encoding scheme incorporates both theme and structure so that musical segments can be joined to generate a piece that is both unique and pleasing to listen to. Each music segment is assigned four hash codes learned by a multi-LSTM system, each defining the given segment's compatibility with other segments for a distinct structural location (beginning, middle, or ending section) in the piece. Additionally, a two-phase music segmentation technique captures structural information while minimizing the segment length. We compare this scheme to multiple recent music generation methods using both objective and subjective evaluation metrics to demonstrate that the pieces generated by our Deep Composer system are not only unique and musically pleasing but also contain more structure and theme features like that of a professionally composed piece. A secondary goal of this research is to bring back the great composers (e.g., Mozart, Chopin, Beethoven, …) to compose their new original music for us today by using their music segments as the building blocks. In fact, the best composers of different times would be able to collaborate today through the Deep Composer. Deep Composer can also generate world fusion music beyond the capacity of any human composers.

    About the speaker:

    Dr. Kien A. Hua is a Pegasus Professor and Director of the Data Systems Lab at the University of Central Florida. He was the Associate Dean for Research of the College of Engineering and Computer Science at UCF. Prior to joining the university, he was a Lead Architect at IBM Mid-Hudson Laboratory, where he led a team of senior engineers to develop a highly parallel computer system, the precursor to the highly successful commercial parallel computer known as SP2. More recently, Prof. Hua was serving as a domain expert on spaceport technology at NASA, and a data analytics expert to advise the U.S. Air Force on the Air Force Strategy 2030 Initiative. Prof. Hua received his B.S. in Computer Science, and M.S. and Ph.D. in Electrical Engineering, all from the University of Illinois at Urbana-Champaign, USA. His current research interest includes music generation,deep learning, multimedia database and analytics, network and wireless communications, and the Internet of Things. He has published widely, with 15 papers recognized as best/top papers at a conference and one as the best paper of the year for a journal. Dr. Hua introduced peer-to-peer communications and data sharing in 1997, that has inspired many impactful applications including the Blockchain technology today. He introduced graph-based data mining at the 1999 International Conference on Data Warehousing and Knowledge Discovery; and the paper was recognized as a best paper at this conference. He is also a pioneer in the Internet of Things. with the WISE (Web-based Intelligent Sensor Explorer) prototype introduced in 2004, probably the first IoT platform implemented. It enables publishing, searching, and sharing of connected sensing devices. More recently, he developed a novelrouter in 2015, that transform network congestion into advantage. His other research works such as Skyscraper Broadcasting, Patching, and Zigzag all have been heavily cited and have inspired many commercial systems in use today. Prof. Hua has served as a Conference Chair, an Associate Chair, and a Technical Program Committee Member of numerous international conferences, and on the editorial boards of several professional journals. More recently, he served as a General Co-Chair for the 2014 ACM Multimedia conference; and he is currently organizing the 2018 IEEE International Conference on Cloud Engineering (IC2E) and serving as a General Co-Chair. Prof. Hua is a Fellow of IEEE.

    PDF

August 09, 2019
  • Title: The curious capacities of quantum channels

    Time: 02:00pm 

    Venue: Room 308, Chow Yei Ching Building, The University of Hong Kong

    Speaker(s): Prof. Debbie Leung

    Remark(s): 

    Prof. Debbie Leung
    Institute for Quantum Computing & Department of Combinatorics and Optimization
    University of Waterloo, Canada

     

    Date: August 9, 2019 Friday

    Time: 2:00 - 3:00pm

    Venue: Room 308, Chow Yei Ching Building, The University of Hong Kong

     

    Abstract:

    The best asymptotic rate of a communication channel to process information (such as transmitting data or creating correlation) is called the capacity of the channel for the task involved. This talk focuses on the capacities of a quantum channel to communicate quantum or private classical data. We first summarize well known surprising results, followed by sharing a few recent developments in the subject.

    About the speaker:

    Debbie Leung joined the Institute for Quantum Computing (IQC) and the Department of Combinatorics and Optimization at the University of Waterloo in 2005. She has been an associate member of the Perimeter Institute since 2019. She was a Tolman postdoctoral fellowship at the Institute for Quantum Information, Caltech, after spending four months at the Workshop on Quantum Computation, September-December 2002, at the Mathematical Sciences Research Institute, Berkeley, and a twoyear stay at the Physics of Information group at the IBM TJ Watson Research Center, 2000-2002. After a BSc in Phys/Math from Caltech in 1995, she did a PhD in Physics at Stanford under the supervision of Professor Yoshihisa Yamamoto and Professor Isaac Chuang. Event website: https://qift.weebly.com/events.html

    PDF

August 08, 2019
  • Title: Building Systems for Machine Learning

    Time: 02:00pm 

    Venue: Room 313, Chow Yei Ching Building, The University of Hong Kong

    Speaker(s): Dr Hong Xu

    Remark(s): 

    Dr Hong Xu
    Department of Computer Science
    City University of Hong Kong

     

    Date: August 9, 2019 Thursday

    Time: 2:00pm

    Venue: Room 313, Chow Yei Ching Building, The University of Hong Kong

     

    Abstract:

    Systems research is critical for machine learning because the recent success of AI and big data is in large part enabled by datacenter-scale computing infrastructures, which employ an army of machines to harness massive datasets in a continuous fashion. In this talk, I will present my research that focuses on systems for machine learning. First, we build a new distributed training system called Stanza that improves the training throughput of parameter server systems by 1.25x to 10.12x. Second, we build a serving system called Saec for recommendation models that reduces the memory footprint of embedding based recommendation models by 27x without performance loss.

    About the speaker:

    Hong Xu is an associate professor in Department of Computer Science, City University of Hong Kong. His research area is computer networking and systems, particularly data center networks and big data systems. He received the B.Eng. degree from The Chinese University of Hong Kong in 2007, and the M.A.Sc. and Ph.D. degrees from University of Toronto in 2009 and 2013, respectively. He was the recipient of an Early Career Scheme Grant from the Hong Kong Research Grants Council in 2014. He received several best paper awards, including the IEEE ICNP 2015 best paper award. He is a senior member of IEEE and member of ACM.

    PDF

August 06, 2019
  • Title: Volumetric Representations: the Geometric Modeling of the Next Generation

    Time: 03:00pm 

    Venue: Room 308, Chow Yei Ching Building, The University of Hong Kong

    Speaker(s): Professor Gershon Elber

    Remark(s): 

    Professor Gershon Elber
    Department of Computer Science
    Technion

     

    Date: August 6, 2019 Tuesday

    Time: 3:00pm

    Venue: Room 308, Chow Yei Ching Building, The University of Hong Kong

     

    Abstract:

    The needs of modern (additive) manufacturing (AM) technologies can be satisfied no longer by boundary representations (B-reps), as AM requires the representation and manipulation of interior fields and materials as well. Further, while the need for a tight coupling between design and analysis has been recognized as crucial almost since geometric modeling (GM) has been conceived, contemporary GM systems only offer a loose link between the two, if at all. For about half a century, (trimmed) Non Uniform Rational B-spline (NURBs) surfaces has been the B-rep of choice for virtually all the GM industry. Fundamentally, B-rep GM has evolved little during this period. In this talk, we seek to examine an extended (trimmed) NURBs volumetric representation (V-rep) that successfully confronts the existing and anticipated design, analysis, and manufacturing foreseen challenges. We extend all fundamental B-rep GM operations, such as primitive and surface constructors and Boolean operations, to trimmed trivariate V-reps. This enables the much needed tight link to (Isogeometric) analysis on one hand and the full support of (heterogeneous and anisotropic) additive manufacturing on the other. Special capabilities toward the support of modern AM and the support of Isogeometric analysis will also be presented, that enable robust queries over the V-reps, including volumetric covering by curves, precise contact analysis, maximal penetration depth, and accurate integration over trimmed domains. Examples and other applications of V-rep GM, including AM and lattice- and micro- structure synthesis (with heterogeneous materials) will also be demonstrated. In collaboration with many others, including Ben Ezair, Fady Massarwi, Boris van Sosin, Jinesh Machchhar, Annalisa Buffa, Giancarlo Sangalli, Pablo Antolin, Massimiliano Martinelli, Stefanie Elgeti, and Robert Haimes.

    About the speaker:

    Gershon Elber is a professor in the Computer Science Department, Technion, Israel. His research interests span computer aided geometric designs and computer graphics. Prof. Elber received a BSc in computer engineering and an MSc in computer science from the Technion, Israel in 1986 and 1987, respectively, and a PhD in computer science from the University of Utah, USA, in 1992. He is a member of SIAM and the ACM. Prof. Elber has served on the editorial board of the Computer Aided Design, Computer Graphics Forum, The Visual Computer, Graphical Models, and the International Journal of Computational Geometry & Applications and has served in many conference program committees including Solid Modeling, Shape Modeling, Geometric Modeling and Processing, Pacific Graphics, Computer Graphics International, and Siggraph. Prof. Elber was one of the paper chairs of Solid Modeling 2003 and Solid Modeling 2004, one of the conference chairs of Solid and Physical Modeling 2010, the chair of GDM 2014, the conference co-chair of SIAM GD/SPM 2015, and the conference co-chair of SPM 2018. He has published over 200 papers in international conferences and journals and is one of the authors of a book titled "Geometric Modeling with Splines - An Introduction". Prof. Elber received the John Gregory Memorial Award, 2011, in "Appreciation for Outstanding Contributions in Geometric Modeling", the Solid Modeling Association pioneers award in 2016, and the Bezier award in 2019. Elber can be reached at the Technion, Israel Institute of Technology, Department of Computer Science, Haifa 32000, ISRAEL. Email: gershon@cs.technion.ac.il, Fax: 972-4-829-5538.

    PDF

July 19, 2019
  • Title: Quantum communication with limited resources

    Time: 02:00pm 

    Venue: Room 328, Chow Yei Ching Building, The University of Hong Kong

    Speaker(s): Dr. Borivoje Dakić

    Remark(s): 

    Dr. Borivoje Dakić
    Faculty of Physics
    University of Vienna

     

    Date: July 17, 2019 Wednesday​

    Time: 2:00 - 3:00pm

    Venue: Room 328, Chow Yei Ching Building, The University of Hong Kong

     

    Abstract:

    Generally speaking, communication is the process of transmitting a message (information) from a sender to a receiver. When the distant parties use a single classical particle to communicate, they are restricted to “one-way signaling”, as the particle can carry information in one direction only. In this talk, I will analyze the corresponding quantum scenario, where the parties communicate via a single quantum particle prepared in superposition of different spatial locations. Surprisingly, I will show that such a scenario results in “multi-way signaling”, which is impossible in classical physics. Our framework [1, 2] does not assume (a priori) the use of quantum entanglement, in contrast to majority of known quantum information tasks and protocols. These findings bring novel insights into quantum information processing, ranging from foundational to practical.

    [1] F. del Santo and B. Dakić, Two-way communication with a single quantum particle, Phys. Rev. Lett. 120, 060503 (2018),
    [2] F. Massa, A. Moqanaki, F. Del Santo, B. Dakić, and P. Walther, Experimental two-way communication with one photon, arXiv:1802.05102 (2018).

    About the speaker:

    Borivoje Dakić is an assistant professor at the Faculty of Physics at the University of Vienna. He obtained his PhD degree in Physics at the University of Vienna. After being a postdoc at the Centre for Quantum Technologies in Singapore and Oxford University, UK, he returned back to Vienna to run an independent research. Since 2016 he is a member of the Foundational Question Institute (FQXi). His expertise lies in the quantum information theory, entanglement characterization and quantum foundations.

    PDF

July 11, 2019
  • Title: The strong converse exponent of classical-quantum channel coding with constant compositions

    Time: 02:00pm 

    Venue: Room 328, Chow Yei Ching Building, The University of Hong Kong

    Speaker(s): Dr. Borivoje Dakić

    Remark(s): 

    Dr. Milán Mosonyi

     

    Date: July 11, 2019 Thursday

    Time: 2:00 - 3:00pm

    Venue: Room 308, Chow Yei Ching Building, The University of Hong Kong

     

    Abstract:

    There are different natural-looking ways to quantify the usefulness of a classical-quantum channel for information transmission. Given a quantum divergence (e.g., a Rényi divergence) and an input distribution P, one can define the corresponding mutual information, which is the divergence "distance" of the joint input-output state from the set of product states with fixed first marginal P. An alternative approach is to measure how spread out the channel states are in the state space, giving rise to the concept of the P-weighted divergence radius. We show that it is this latter notion that admits an operational interpretation in the context of constant composition channel coding, with the divergence being the sandwiched Rényi divergence.

    About the speaker:

    Milán Mosonyi obtained his PhD in theoretical physics in 2005 at the Catholic University of Leuven, under the supervision of Mark Fannes and Dénes Petz. He has been an assistant professor (since 2005) and later an associate professor (since 2012) at the Institute of Mathematics, Budapest University of Technology and Economics. Between 2006 and 2016 he was in research positions at Tohoku University, National University of Singapore, University of Bristol, Autonomous University of Barcelona, and the Technical University of Münich. His main research interests are quantum Shannon theory and mathematical physics.

    PDF

June 30, 2019
June 11, 2019
  • Title: Internet of Video Things (IoVT): Next Generation IoT with Visual Sensors

    Time: 03:30pm 

    Venue: Room 308, Chow Yei Ching Building, The University of Hong Kong

    Speaker(s): Professor Chang Wen Chen

    Remark(s): 

    Professor Chang Wen Chen
    The Chinese University of Hong Kong, Shenzhen China &
    State University of New York at Buffalo, USA

     

    Date: June 11, 2019 Tuesday

    Time: 3:00pm

    Venue: Room 308, Chow Yei Ching Building, The University of Hong Kong

     

    Abstract:

    The worldwide flourishing of the Internet of Things (IoT) in the past decade has enabled numerous new applications through the internetworking of a wide variety of devices and sensors. More recently, visual sensors has seen their considerable booming because they usually capable of providing richer and more versatile information. Internetworking of large scale visual sensors has been named Internet of Video Things (IoVT). IoVT has its own unique characteristics in sensing, transmission, storage, and analysis, which are essentially different from conventional IoT. These new characteristics of IoVT are expected to impose significant challenges to existing technical infrastructures. In this talk, an overview of recent advances in various fronts of IoVT will be introduced and a broad range of technological and system challenges will be presented.

    About the speaker:

    Chang Wen Chen is currently Dean of School of Science and Engineering at the Chinese University of Hong Kong, Shenzhen. He is also an Empire Innovation Professor of Computer Science and Engineering at the University at Buffalo, State University of New York since 2008. He was Allen Henry Endow Chair Professor at the Florida Institute of Technology from July 2003 to December 2007. He was on the faculty of Electrical and Computer Engineering at the University of Rochester from 1992 to 1996 and on the faculty of Electrical and Computer Engineering at the University of Missouri-Columbia from 1996 to 2003. He has been the Editor-inChief for IEEE Trans. Multimedia from January 2014 to December 2016. He has also served as the Editor-inChief for IEEE Trans. Circuits and Systems for Video Technology from January 2006 to December 2009. He has been an Editor for several other major IEEE Transactions and Journals, including the Proceedings of IEEE, IEEE Journal of Selected Areas in Communications, and IEEE Journal of Emerging and Selected Topics in Circuits and Systems. He has served as Conference Chair for several major IEEE, ACM and SPIE conferences related to multimedia video communications and signal processing. His research is supported by NSF, DARPA, Air Force, NASA, Whitaker Foundation, Microsoft, Intel, Kodak, Huawei, and Technicolor. He received his BS from University of Science and Technology of China in 1983, MSEE from University of Southern California in 1986, and Ph.D. from University of Illinois at Urbana-Champaign in 1992. He and his students have received nine (9) Best Paper Awards or Best Student Paper Awards over the past two decades. He has also received several research and professional achievement awards, including the Sigma Xi Excellence in Graduate Research Mentoring Award in 2003, Alexander von Humboldt Research Award in 2009, the University at Buffalo Exceptional Scholar – Sustained Achievement Award in 2012, and the State University of New York System Chancellor’s Award for Excellence in Scholarshipand Creative Activities in 2016. He is an IEEE Fellow since 2004 and an SPIE Fellow since 2007.

    PDF




Department of Computer Science
Rm 301 Chow Yei Ching Building
The University of Hong Kong
Pokfulam Road, Hong Kong
香港大學計算機科學系
香港薄扶林道香港大學周亦卿樓301室

Copyright © Department of Computer Science, Faculty of Engineering, The University of Hong Kong. All rights reserved.

Privacy Policy
Don't have an account yet? Register Now!

Sign in to your account