为拓展学生全球视野和培养“会语言、通规则、精领域”的全球胜任力,计算机学院着力建设国际化育人资源,推出系列高水平国际学术专题报告。现对9月份即将举办的国际学术报告会内容进行预告,欢迎同学们在线预约。
下面对9月份开设的国际学术报告会进行相关介绍。
报告一:3D Vision: The Feature Correspondence Problem for 3D Data
主讲人:杨佳琪
2014年和2019年于华中科技大学获得学士和博士学位,2017年至2018年在宾夕法尼亚大学进行公派联合培养,目前为西北工业大学计算机学院副教授、西北工业大学空天地海一体化大数据应用技术国家工程实验室多域多维信息系统负责人。其主要研究方向为点云特征提取、匹配以及三维配准重建。
报告简介:In this talk, I will Introduce the concept, background and applications of 3D vision. Then, the talk will focus on a typical 3D vision problem, i.e., 3D feature correspondence between 3D data. Here, we will include some popular methods and briefly talk about the technical details. At last, we will discuss about the research direction in this area and see if interesting ideas can be found in the class.
报告时间、地点:9月6日19:00——20:30
报告地点:计算机学院四楼拐角会议室
报告二:Vision-language interaction: technologies behind applications
主讲人:牛凯
计算机学院副教授。2015年于中国科学技术大学自动化系,获得工学学士学位;2020年于中国科学院自动化研究所模式识别国家重点实验室,获得工学博士学位。博士毕业后于2020年10月加入西北工业大学计算机学院,任职副教授,从事计算机科学与技术学科方向的教学及科研工作。长期专注于多模态数据分析、计算机视觉、模式识别等相关领域的科学研究工作,特别是在视觉-语言交互前沿领域,以第一作者发表包括IEEE TIP, ACM MM, PR等在内的多篇国际高水平学术论文。
报告简介:The goal of this course is to give students an understanding of many vision-language interaction tasks that can be seen everywhere in our daily life, to understand the latest technologies behind these applications, and to look forward to the future development of AI technology.
The course is organized into three parts: 1. introduction to the vision-language interaction applications, 2. task abstraction and definition, and 3. the key technologies in solution. In part one, several common vision-language interaction tasks are introduced, including their application scenarios, characteristics, and so on. Part two shows the way that scientists and engineers give abstraction and definition of these application problems for further studying. The last part gives detailed explanations of the key technologies for solving these problems.
报告时间:9月16日19:00——20:30
报告地点:计算机学院四楼拐角会议室
报告三:Recent Advances in Image Semantic Segmentation
主讲人:刘婷
现任西北工业大学计算机学院副教授。于2015年获得北京交通大学计算机科学与技术硕士学位,2020年获得北京交通大学信号与信息处理博士学位。曾在各大顶级期刊和会议上发表过多篇学术论文,如IEEE TIP,IEEE TMM,IEEE TIE,ACM MM,AAAI,ICME等。研究范围主要包括语义分割和图像生成。
报告简介:Image semantic segmentation has been a very hot topic in recent years due to its tremendous applicable value. Nowadays, it has benefitted from the successes of deep learning in the field of computer vision. Although a large number of semantic segmentation networks have been reported and make great progress, the current methods suffer from some challenges, such as the model generalization ability, models seriously depend on labeled data. Many recent methods have been developed to address these problems in an unsupervised or weakly supervised manner. This talk will give a brief introduction to some classic methods and a detailed summary of recent advances in this field.
报告时间:9月23日19:00——20:30
报告地点:计算机学院四楼拐角会议室
报名须知:
国际学术报告会属于国际化必修学分的考核范围;
每场报告会25人,每学期10-12次,集中考试月原则上不开设报告会;
每次报告会的人数是有限制的,原则上选了报告必须出席,如若两次以上未出席,将会取消近一个月的报名资格。
请扫描以下二维码或点击链接进行报名。
报名链接:https://www.wenjuan.com/s/7RbuauM/#
(审稿:高峻)