講座主題：What Can We Do with Big AI Models for Visual and Multimedia Computing?
專(zhuān)家姓名：Weisi Lin
工作單位：新加坡南洋理工大學(xué)
講座時(shí)間：2025年08月23日 14:00-15:00
講座地點(diǎn)：科技館5208
主辦單位：煙臺(tái)大學(xué)計(jì)算機(jī)與控制工程學(xué)院
內(nèi)容摘要：
Although this is not the first time AI has become a hot topic in history, it is the first time AI is so close to ordinary citizen’s life. In a very short period, large models have also revolutionized our research, since, like it or not, we must work with them as co-pilots in rapidly increasing situations. In this talk, I will share some recent research attempts to perform visual computing in the context of big AI models, e.g., text-assisted segmentation of occluded objects, selection of core datasets, technical and aesthetic image quality assessment, and pruning and quantization of models themselves. Possible related future research topics are to be discussed as well, including extension to true multimedia (smell, touch, etc.).
主講人介紹：
Weisi Lin is an active researcher in image processing, perception-based signal modelling and assessment, video compression, and multimedia communication. He had been the Lab Head, Visual Processing, Institute for Infocomm Research (I2R), Singapore. He is currently a President’s Chair Professor in College of Computing and Data Science, Nanyang Technological University (NTU), Singapore, where he also serves as the Associate Dean (Research). He is a Fellow of IEEE and IET. He has been awarded Highly Cited Researcher since 2019 by Clarivate Analytics, and elected for the Research Award 2023, College of Engineering, NTU. He has been a Distinguished Lecturer in both IEEE Circuits and Systems Society (2016-17) and Asia-Pacific Signal and Information Processing Association (2012-13). He has been an Associate Editor for IEEE Trans. Neural Networks Learn. Syst., IEEE Trans. Image Process., IEEE Trans. Circuits Syst. Video Technol., IEEE Trans. Multim., IEEE Sig. Process. Lett., Quality and User Experience, and J. Visual Commun. Image Represent., as well as a Senior Editor for IEEE J. Selected Topics in Sig. Process. He has been a TP Chair for several international conferences, and is a General Co-Chair for IEEE ICME 2025 and the Lead General Chair for IEEE ICIP 2027. He believes that good theory is practical and has delivered 10+ major systems for industrial deployment with the technology developed. He has been the Programme Lead for the Temasek Foundation Programme for AI Research, Education & Innovation in Asia, 2020-2024.
