Report title:The development and future perspectives of Al models from our own practices
Report location: Information Building535Lecture Hall
Report time:2023Year05month04Sunday (Thursday) morning9Points30points
Reporter: Fang Hui
Personal introduction:Dr. Fang Hui is currently a professor at the School of Software, Dalian University，Associate Professor, School of Computing, Loughborough University, UK，2006Received PhD from University of Bradford, UK。Later engaged in postdoctoral research and teaching positions seabet mobile in many British universities。The main research field is comparative learning、Transfer learning、Multimodal fusion，Multimedia signal processing and visual analysis, etc.，atIEEE Conference on Computer Vision and Pattern Recognition (CVPR，CCF AClass Conference)，AAAI Conference on Artificial Intelligence (AAAI，CCF AClass Conference)，IEEE Transactions on Visualization and Computer Graphics （CCF AClass, Chinese Academy of Sciences1District, impact factor5.226），Pattern Recognition （CCF BClass, Chinese Academy of Sciences1District, impact factor8.518），IEEE Transactions on Multimedia（CCF BClass, Chinese Academy of Sciences1District, impact factor8.182），IEEE Transactions on Circuits and Systems for Video Technology （CCF BClass, Chinese Academy of Sciences1District, impact factor5.859) and other internationally renowned academic journals and conferences published60Remaining papers。Host and participated in many national-level projects，Have sufficient project research experience。
Abstract:Advanced AI techniques have been developed rapidly in recent years. Many deep neural network seabet sports betting models have been successfully applied in real-world applications. However, several key challenges hinder the further use of these new models more widely. In this talk, after identifying these challenges, our possible solutions are discussed to shed light on future perspectives of AI techniques. I will present our recent papers, including weakly supervised learning, attention-based models, contrastive learning, few shot based learning, spiking neuron network and their applications.
