Abstract
Video and visual applications demand at the same time, very high computational power, very high on- and off-chip communication bandwidth, and low latency, while presenting a high degree of data dependency and input dependency, making it extremely inefficient to be processed on existing computing platforms such as CPU, GPU and NPU. In this talk, we analyze key challenges in building real-time, ultra high resolution, low latency intelligent video systems, present some potential solutions with showcase applications. Going beyond video for human consumption, we then overview our work in ultra low power computer vision for ubiquitous AI using the same design methodology.
Biography
Jiangtao (Gene) Wen received the BS, MS and Ph.D. degrees with honors from Tsinghua University, Beijing, China, in 1992, 1994 and 1996 respectively, all in Electrical Engineering. From 1996 to 1998, he was a Research Fellow at UCLA, where he conducted research on multimedia coding and communications. Many of his inventions were later adopted by international standards such as H.263, MPEG and H.264. Some of his inventions were licensed to Samsung Electronics in the biggest patent licensing agreement in the highly ranked and world-renowned UCLA School of Engineering.After UCLA, he was a co-founder and played the technology leadership role in PackVideo Corp (acquired by NTT DoCoMo, NASDAQ: DCM), Mobilygen (acquired by Maxim, NASDAQ: MXIM), Ocarina Networks (acquired by Dell, NASDAQ: DELL), Ortiva Wireless (acquired by Allot Communications, NASDAQ: ALLT), and QuickFire Networks (acquired by Facebook, NASDAQ: FB/Meta). He has made instrumental contributions to the standardization and productization of multimedia technologies and products including mobile video applications, low power ASIC design for handheld devices, large-scale storage systems and wireless multimedia streaming technologies. Products embodying technologies he invented and developed under his leadership are currently serving over 2 billion users worldwide. Since 2008, Dr. Wen has held a Professorship at the Department of Computer Science and Technology of Tsinghua University. He was a Visiting Professor at Princeton University in 2010 and 2011. He has authored many widely referenced papers and holds 40 granted US patents with numerous others pending. Among the numerous honors he received are the 2010 IEEE Trans. CSVT Best Paper Award, a nomination for the 2016 IEEE Trans CSVT Best Paper Award, back-to-back gold medals in the 2018 and 2019 Salon International Des Inventions Geneva, a 2020 Red Dot Best of the Best Award, the 2018 IEEE Capocelli Prize, Google Faculty Award 2018, 1st Place in the 2017 IEEE ICME Twitch Grande Challenge, Finalist for the World's First 10K Best Paper Award at ICME 2017, 2016-2017 Asia Pacific Signal and Information Processing Association Distinguished Lecturer and the 2016 Frost & Sullivan Global Enabling Technology Leadership Award. Dr. Wen was elected a Fellow of the IEEE in 2011, and named one of Fortune Magazine Global Chinese 100 in 2023. Besides teaching and conducting research, Dr. Wen also invests in high technology companies as an angel investor.