Media SW Engineering Director
Faouzi Kossentini received the B.S., M.S., and Ph.D. degrees from the Georgia Institute of Technology, Atlanta, Georgia, United States of America, in 1989, 1990, and 1994, respectively. Dr. Kossentini has since August 2017 been a Media SW Engineering Director of the Visual Cloud Division of the Data Center Group at Intel Corporation. From late 2009 to July 2017, he had been the President and Chief Executive Officer of eBrisk Video, a Canadian company that he founded and that specializes in the area of H.265/HEVC-based video communications. eBrisk Video was a leader in the development of H.265/HEVC encoding products for video streaming and broadcast applications.From 2006 to 2008, Dr. Kossentini had been the Director of Technology, Encoder Products, for Digital Media Networks, Service Provider Video Technology Group, Cisco. Then, Dr. Kossentini led a team of market researchers and technology leaders, whose aim was to create encoder product development strategies given the market demands and the available encoding technologies. Dr. Kossentini had also continued to serve as the General Manager of UB Video Tunisia, a Company he founded in 2003, and that was acquired by Cisco in February 2006.From 2000 to 2006, Dr. Kossentini had been the President and Chief Executive Officer of UB Video, which he founded and made a world-wide leader in the development of H.264/AVC-based video encoding solutions, developing products that are still widely used today in the video conferencing and broadcast markets. UB Video was also acquired by Cisco in February 2006.From 1996 to 2003, Dr. Kossentini had been an assistant professor and then an associate professor at the department of Electrical and Computer Engineering at the University of British Columbia, doing research in the areas of signal processing, communications and multimedia. Then, he had also been a technical consultant to various North American companies such as Image Power, where he had also acted as Chief Technology Officer from 1998 to 2000.From 1994 to 1995, Dr. Kossentini had been a Research Scientist at Nichols Research Corporation (Huntsville, Alabama), which develops various technical products and solutions for NASA and the US Department of Defense.Dr. Kossentini has co-authored almost 300 journal papers, conference papers, book chapters, patents, standards contributions and popular technical white papers. He has also led in numerous international ISO and ITU-T activities involving the standardization of JBIG-2, JPEG-2000, H.263, H.264/AVC and H.265/HEVC.Dr. Kossentini is a senior member of the IEEE. He had served the IEEE as a Vice General Chair for the 2000 International Conference on Image Processing, and as an associate editor for the Transactions on Image Processing and the Transactions on Multimedia. More recently, he has also served the IEEE as the Technical Chair for the 2008 International Conference on Image Processing, in the area of Implementation of Image and Video Processing Systems.
演讲:Accelerated Growth of the Visual Cloud Through Open Sourcing SVT-HEVC and SVT-AV1
2018-10-20 11:00 - 11:45
The world is today witnessing a revolutionary transformation in the areas of media delivery, processing and consumption. Not only the internet traffic is already dominated by the exchange of visual information but also the visual cloud has become of the center of such traffic. Towards a fast-growing visual cloud, with underlying mostly-Xeon-populated homogeneous data centers, Intel Corporation is now leading the way with an Open Source SW-centric strategy. Intel is already open sourcing its SVT-HEVC encoder in Q3’2018, and it also plans to open source the SVT-AV1 encoder in Q2’2019. Such will increase adoption and decrease the cost of HEVC and AV1 by our visual cloud customers, helping them to accelerate the growth of their visual cloud applications. We will discuss briefly Intel’s current visual cloud SW strategy as well as provide detailed descriptions of the being-open-sourced SVT-HEVC encoder and the soon-to-be-open-sourced SVT-AV1 encoder. We will also present results that will illustrate the performance-quality tradeoffs of each of the SVT-HEVC and SVT-AV1 encoders. Finally, we will invite our visual cloud customers to participate in the development and growth of the new SVT-HEVC and SVT-AV1 Open Source communities.
Point cloud data has been emerging and popular for various applications including virtual reality (VR), augmented reality (AR), plus many other computer vision problems. Comparing to conventional image/video data, several fundamental challenges need to be addressed, e.g., its large data rate, irregular sampling structure, varying geometric as well as associated attributes. In this talk, we first review recent progress in point cloud compression and an ongoing MPEG standardization attempt. A framework to conduct fast point cloud resampling is then presented based graph signal processing, which could be utilized to scale down the complexity of many point cloud processing tasks. Last, deep neural networks (DNNs) are generalized for native supporting on point clouds as a new type of signal. For one example, a folding-based autoencoder (AE) architecture FoldingNet is introduced with great potentials for point cloud classification tasks. In short, fundamental techniques are highlighted how point clouds could be successful with more efficient compression, processing and understanding.
Debargha Mukherjee
The Alliance for Open Media - a consortium of major Internet companies formed in 2016 with the mission to develop open media formats for the web - closed their first video codec AV1 in June of 2018. AV1 is the best standardized video codec available today that is also royalty-free. This talk will provide a high level overview of the coding tools in AV1, with special attention to the tools and features that are industry-first in standardized codecs. Results on standard tests sets will be provided.