Industry Workshops


Tencent industry workshop

Session title: TBA

Organize date: Sep. 23

Organize room: 201BC

Brief description: TBA

Speakers: TBA


Kuaishou industry workshop

Session title: User Experience Driven Short-Video Streaming System Optimization

Organize date: Sep. 23

Organize room201DE

Brief description:

As a unicorn in mobile video industry of China, Kuaishou commits herself to building a universal, equal, and harmonic platform for short video streaming and live video broadcasting.  In this workshop, the experts from Kuaishou will bring their techniques and methods about optimizing the whole platform towards improving user experience. The workshop consists of two talks.

Talk 1: Short Video Streaming System and Technique Optimization

In this talk, the eco-system of Kuaishou short video streaming will be introduced. The system ranges from content production to consumption. It includes content capturing, editing, transcoding, transmission, consuming, and data analysis. Firstly, the overview of the architecture for short video sharing will be introduced. Second, the audio and video techniques which are used in this system to improve user experience are also presented. Furthermore, how to use big data analysis methods to guide the optimization will also be elaborated.

Speaker 1: Yunfei Zheng

Yunfei Zheng received his B.S. degree and M.S. degree from Tsinghua University in 1999 and 2002 respectively.  He received his Ph.D. degree in Electrical and Computer Engineering from West Virginia University, US in 2008. His main research areas are video modeling, video coding, video/image processing, and computer vision. He joined Princeton research lab of Thomson in 2008 and focused on the research of next generation video coding technique. In 2010, he joined Qualcomm and committed himself to HEVC standardization. His multiple proposals were adopted by HEVC standard. In 2011, he joined Apple Inc. and joined many projects, which covers video coding and video/image understanding, such as core code development for FaceTime/iTunes, and low-level video/image analysis algorithms in iOS memories feature. In 2018, he joined Kuaishou as a director to lead the video algorithm and engineering team, which provides core algorithm support for the company’s business.

Talk 2: Non-reference Non-Uniform Distorted Video Quality Assessment Based on Deep Multiple Instance Learning

The different parts of one non-uniform distorted video have different distortion degrees, thereby leading to data ambiguity in a data set. When non-uniform distorted video blocks are used as input, traditional machine learning-based methods frequently do not work effectively or may even fail. In this talk, we will present a novel multiple instance (MI) learning method to overcome this non-uniform distortion problem. How this video quality assessment was used in Kuaishou’s business to improve user experience will be also introduced.

Speaker 2: Mading Li

Mading Li received his B.S. degree in computer science from Peking University in 2013, and Ph.D. degree from Institute of Computer Science & Technology of Peking University in 2018. He was a Visiting Scholar with McMaster University, ON, Canada from 2016 to 2017. He is currently an algorithm engineer with Video Technology Team at Kuaishou, China,in which he is focusing on image/video quality evaluation and smart video editing.


Google industry workshop

Session title: TBA

Organize date: Sep. 24

Organize room: 201BC

Brief description: TBA

Speakers: TBA


Qualcomm industry workshop

Session title: Depth Sensing on Mobile Phones

Organize date: Sep. 24

Organize room: 201DE

Brief description:

This session is an introduction to SLiM - an implementation of the Qualcomm depth sensing reference design by Himax. The workshop will center around a demo of the SLiM depth sensing module and its capabilities. The performance of the module is discussed and its usage along with several reference applications implemented using the provided SDK.

Speakers 1: Champ Yen

Champ Yen is an Application Engineer at Qualcomm Taiwan Corporation.  He received a B.S. degree in computer science information engineering from the National Cheng Kung University in 2001, and a M.S. degree in computer science information engineering from the National Chao Tung University of Taiwan in 2003. He provides support for customer application development, including algorithm porting, problem solving, and technical support.  Champ has significant experience in GPGPU, DSP and domain specific programming.  In recent years he has worked specifically on optimization and development of camera and computer vision applications.


Facebook industry workshop

Session title: Video processing at Facebook - how to increase quality and power efficiency at scale

Organize date: Sep. 25

Organize room: 201BC

Brief description:

Facebook is the world's largest social network, offering a variety of products that support video, such as Facebook Live, Facebook Watch, Instagram TV (IGTV), Messenger and WhatsApp video calling and Oculus/Portal hardware that allow user immersion. We handle both premium and user-generated content at varying source qualities and we are making it available all over the world over highly variable network conditions. We use adaptive bitrate streaming to maximize quality but also end-to-end encryption to protect our members’ privacy. Video processing is taking place in our own datacenters, where our focus is on the highest level of security, availability, quality and energy efficiency. In our session we will cover topics such as how we measure video quality at scale, what we do to maximize such quality and what steps we take to reduce the energy requirements of all video processing in our datacenters. We will highlight some of our research initiatives in this space and include a panel discussion with world experts on what are the challenges and possible research directions in efficient video processing.

Speakers 1: Dr. Ioannis Katsavounidis

Dr. Ioannis Katsavounidis is a member of Video Fundamentals and Research, part of the Video Infrastructure team, leading technical efforts in improving video quality across all video products at Facebook. Before joining Facebook, he spent 3.5 years at Netflix, contributing to the development and popularization of VMAF, Netflix's video quality metric, as well as inventing the Dynamic Optimizer, a shot-based video quality optimization framework that brought significant bitrate savings across the whole streaming spectrum. Before that, he was a professor for 8 years at the University of Thesally's Electrical Engineering Department in Greece, teaching video compression, signal processing and information theory. He has over 100 publications and patents in the general field of video coding, but also high energy experimental physics. His research interests lie in video coding, video quality, adaptive streaming and hardware/software partitioning of multimedia processing.

Speakers 2: Dr. Mani Malek Esmaeili

Mani Malek Esmaeili received his PhD at University of British Columbia. His research interests are multimedia retrieval, computer vision, and the general problem of approximate nearest neighbor search. He has been working at Facebook’s video infrastructure group as an algorithm developer. He has been leading the Media copyright’s team algorithm development for the past year.

Speakers 3: Rahul Gowda

Rahul Gowda is a member of Video Fundamentals and Research at Facebook helping build key video infrastructure pieces to serve video@scale. Prior to joining Facebook, he spent 8 years at Nvidia working on cloud gaming, GPU encoding and streaming. He received a Masters in EE from Arizona State University. His research interests lie at the intersection of video coding, gaming, adaptive streaming and hardware/software co-design of multimedia processing.


Microsoft industry workshop

Session title: TBA

Organize date: Sep. 25

Organize room: 201DE

Brief description: TBA

Speakers: TBA