报告问题:When Visual Perceptual AI Meets with Generative AI
报告人:Jenq-Neng Hwang教授(University of Washington)
报告时间:2024年7月18日14:00
主持人:杜海清
腾讯聚会:541-782-135
报告摘要:
With the fast technological advances on artificial intelligence (AI), both on visual perceptual AI and the more recent generative AI in the past decade, it is widely expected to envision AI’s potential to revolutionize all industries by making it more accessible, efficient, and effective. More specifically, perceptual AI models have been successfully applied to classification, detection, semantic/instance segmentation and human pose estimation on various visual tasks with different data modalities. On the other hand, generative tasks, such as image and text generation, can leverage huge amounts of web-sourced data for pre-training, with minimal amount of laborious human-labeled ground truth. This motivates us to effectively combine these two AI paradigms to achieve better performance than that can achieved by only one of the AI paradigms. In this talk, I will present some of our attempts on combing both perceptual AI and generative AI for several tasks, such as 1). DriveLLM for autonomous driving planning facilitated by 3D object detections; 2). Improved 3D human pose estimation via diffusion based prior optimization; 3). classifier guided diffusion generation of X-ray medical report; and 4). Zero or few shot of class incremental learning.
报告人先容:
Dr. Jenq-Neng Hwang received the BS and MS degrees, both in electrical engineering from the National Taiwan University, Taipei, Taiwan, in 1981 and 1983 separately. He then received his Ph.D. degree from the University of Southern California. In the summer of 1989, Dr. Hwang joined the Department of Electrical and Computer Engineering (ECE) of the University of Washington in Seattle, where he has been promoted to Full Professor since 1999. He served as the Associate Chair for Research from 2003 to 2005, and from 2011-2015. He also served as the Associate Chair for Global Affairs from 2015-2020. He is currently the International Programs Lead in the ECE Department. He is the founder and co-director of the Information Processing Lab., which has won several AI City Challenges awards in the past years. He has written more than 400 journal, conference papers and book chapters in the areas of machine learning, multimedia signal processing, computer vision, and multimedia system integration and networking (myGoogle citation), including an authored textbook on "Multimedia Networking: from Theory to Practice," published by Cambridge University Press. Dr. Hwang has close working relationship with the industry on artificial intelligence and machine learning.
Dr. Hwang received the 1995 IEEE Signal Processing Society's Best Journal Paper Award. He is a founding member of Multimedia Signal Processing Technical Committee of IEEE Signal Processing Society and was the Society's representative to IEEE Neural Network Council from 1996 to 2000. He is currently a member of Multimedia Technical Committee (MMTC) of IEEE Communication Society and also a member of Multimedia Signal Processing Technical Committee (MMSP TC) of IEEE Signal Processing Society. He served as associate editors for IEEE T-SP, T-NN and T-CSVT, T-IP and Signal Processing Magazine (SPM). He served as the General Co-Chair of 2021 and 2022 IEEE World AI IoT Congress, Seattle, WA. He also served as the Program Co-Chair of IEEE ICME 2016 and was the Program Co-Chairs of ICASSP 1998 and ISCAS 2009. Dr. Hwang is a fellow of IEEE since 2001.