An overview of the progress and challenges in neural image compression
George Toderici, Google
Neural compression methods have started gaining in popularity after a relatively long break during the AI winter. Their appeal lies in their flexibility and the ease with which they can be adapted to various domains. In this talk I will concentrate on the field of neural image compression, and will discuss the progress that has been made, making this class of methods the most performant type of compression algorithms for images. I will discuss the many challenges that remain before these methods can be fully deployed, and I will address the exciting new directions in which this technology hasn't been fully explored.
George Toderici is a research scientist / TLM of the Neural Compression team in Google Research. He and his team are exploring new methods for compression of multimedia content using techniques inspired from the neural network domain. Previously he has worked on video classification tasks based on classical methods as well as more modern neural network-based methods. Dr. Toderici has been involved in organizing the first and second Workshop and Challenge on Learned Image Compression (CLIC 2018-2022 at CVPR), the first and second YouTube-8M workshop at CVPR 2017, ECCV 2018, ICCV 2019, the THUMOS 2014 workshop at ECCV, and is one of the co-authors of the Sports-1M and Atomic Video Actions (AVA) datasets. Previously he has served as a Deep Learning area co-chair for ACM Intl. Conf. on Multimedia (MM) in 2014, In addition, he has served in the program committees of CVPR, ECCV, ICCV, ICLR and NIPS for numerous years. His research interests include deep learning, action recognition and video classification.