【講演概要】More than 80% of the information obtained by human beings comes from vision, and we call the media that carry visual information, i.e., images, videos and three-dimensional geometry, visual media. As interdisciplinary research that combines aspects of computer graphics, computer vision, image and video processing, geometric computing, and machine learning, visual media computing is an important means for human to understand and reform the real world. In this talk, I will introduce our efforts on building the foundation of visual media computing from the aspects of algorithms and frameworks. In particular, I will introduce our proposed basic backbone networks for visual media deep learning, deep learning framework, and deep learning techniques for foundation models, including heterogeneous computing platforms, efficient training and inferencing for foundation models.
【略歴】Shi-Min Hu is currently a professor in the Department of Computer Science and Technology, Tsinghua University. He received his Ph.D. degree from Zhejiang University in 1996. His research interests include digital geometry processing, video processing, rendering, computer animation, computer aided geometric design and deep learning. He has published more than 100 papers in journals and refereed conferences. He is the Editor-in-Chief of Computational Visual Media , and on the editorial boards of several journals, including Computer Aided Design and Computer & Graphics. Professor Hu is a member of Chinese Academy of Science, an IEEE Fellow and winner of CCF Wang Xuan Award.