Co-Founder, President & Chief Scientist
Zoe Liu is Co-Founder, President, and Chief Scientist of Visionular, a startup that has just been incorporated aiming for the smoothest delivery of videos at the highest quality. Zoe was previously a software engineer with the Google Chrome Media team for five years, and has been a key contributor to the development and finalization of the open source video codec standard AOM/AV1. Zoe received her PhD/ME/BE from Tsinghua University and her second PhD from Purdue University. Either as a principal contributor or as a Technical Lead, Zoe had once devoted her effort to the design and development of several renowned video call products, including Apple's FaceTime, Tango Video Call, and Google Glass Video Call. Zoe has accumulated years of innovative research experiences at prestigious research labs, including Bell Labs, Nokia Research Center, Sun Labs, and HP Labs, and in particular excels in cross-field effort. Zoe has published 40 international conference and journal papers, and filed over 50 patents worldwide. She has been selected as a 2018 Google I/O speaker to introduce AV1 to the worldwide developers. She has delivered keynote speeches in both LiveVideoStackCon 2017 and WebRTCon 2018.
演讲：Emerging AV1 Video Codec - Novel Inter and Intra Prediction Tools Under Consideration
2017-10-21 10:00 - 10:45
Google started the WebM Project in 2010 to develop open source, royalty-free video codecs designed specifically for media on the Web. The second generation codec released by the WebM project, VP9, is currently served by YouTube, and enjoys billions of views per day. Realizing the need for even greater compression efficiency to cope with the growing demand for video on the web, the WebM team embarked on an ambitious project to develop a next edition codec AV1, in a consortium of major tech companies called the Alliance for Open Media (AOM), that achieves at least a generational improvement in coding efficiency over VP9. In this talk, we focus primarily on the new tools developed by AV1, including the tools and coding modes for the prediction of pixel blocks that improve intra, inter and combined inter-intra prediction, as well as new paradigms for transform, interpolation filtering, coefficient entropy-coding, super-resolution, and restoration filtering.