武庆明(Jonathan Wu)教授学术报告

作者:发布时间:2019-08-09浏览次数:387

报告题目:Vision, Gesture, and Machine Learning in Multimodal Human-Machine Interaction
报告时间:2018年11月15日(星期四)上午9:00-12:00
报告地点:2教南二楼228学院会议室

报告主要内容
  Interaction between humans, by nature, is a multimodal process, combining different elements, such as vision, gesture, speech, eye gaze, facial expression, emotions, and touch. The traditional uni-modal implementation of human-machine interfaces (HMI) fail to meet the standards of performance effectiveness of human-human interactions. Thus, the recent cutting-edge technologies shift their attention to multimodal information processing,whichmimics the natural interaction betweenhumans.

  This talk presents an overview of some research works that have been conducted by the presenter, which could be extended and utilized as integral components of a multimodal human-machine interaction system. The research includes foreground identification, crowd counting, facial expression recognition, people tracking, and human gesture/activity recognition. The application of the works is aimed towards developing intelligent transportation systems, surveillance and security, vision-guided robotics, and autonomous driving, among others. Many of these proposed approaches are based on machine learning (ML) or deep learning (DL).

报告人简介:
  武庆明,教授,博士生导师,计算机视觉和传感系统研究所主任,加拿大汽车电子和信息系统领域首席科学家,现工作于加拿大温莎大学 (University of Windsor) 电子工程系,在智能系统与多媒体信息处理领域有较高的影响力。武教授先后主持完成了包括加拿大国家科学与工程研究项目(NSERC),国际合作重大项目、加拿大国家重点基金等在内的多个国家或国际项目,至今共培养博士、博士后40余人。武教授长期从事计算机视觉、多媒体信息处理,智能系统的研究工作,出版了关于3D视觉的学术专著一部,以及350余篇学术论文,其中SCI收录论文120余篇,IEEE系列汇刊50余篇,担任了包括IEEE TNNLS,IEEE TCYB, IEEE SMC-Systems, IJCA等在内的多个国际知名杂志副主编。