NSF East Asia and Pacific Summer Institute (EAPSI) for FY 2013 in China

这项行动资助了亚利桑那州立大学的Samuel Fuller Dodge于2013年夏天在中国北京大学进行计算机与信息科学与工程领域的研究项目。这个项目的题目是“受生物学启发的计算机视觉：利用注意力有效地处理视觉实体”。主持人是王一舟博士。本项目研究生物启发视觉注意模型在计算机视觉应用中的有用性。人类的视觉系统能够通过选择性地将注意力集中在场景中最显著的区域，利用相对较少的生理资源处理大量信息。这种相同的信息处理方式在类似计算约束下的计算机视觉系统中是有用的。为此，本项目研究了简单的自下而上注意力和更复杂的自上而下注意力对物体识别和场景理解应用的相对影响。自下而上的注意力是由吸引我们注意力的低层次特征形成的，比如蓝点海洋中的红点。自上而下的注意力源于更高层次的认知处理，比如在场景中发现一张脸。这两个因素结合在一起，可以产生一个更合适的注意力模型，用于计算机视觉识别任务。EAPSI奖学金的广泛影响包括为研究员提供美国以外的第一手研究经验；介绍该地区的科学、科学政策和科学基础设施；以及对社会、文化和语言的了解。这些活动符合美国国家科学基金会的目标，即在其科学家、工程师和教育工作者的职业生涯早期培养国际合作，从而确保美国科学劳动力具有全球意识。此外，本研究的成果将在顶尖的计算机视觉会议上传播，使本研究能够在自动化、医疗保健和智能系统等实际应用领域中得到应用。他正在帮助中国的研究生和本科生提高他们的专业英语水平，以便他们为会议做更多的准备。

This action funds Samuel Fuller Dodge of Arizona State University to conduct a research project in the Computer and Information Science and Engineering area during the summer of 2013 at Peking University in Beijing, China. The project title is "Biologically Inspired Computer Vision: Using Attention to Efficiently Process Visual Entities." The host scientist is Dr. Yizhou Wang.This project studies the usefulness of biologically inspired visual attention models in computer vision applications. The human visual system is able to process a large amount of information using relatively few physiological resources by selectively focusing attention on the most salient areas of a scene. This same manner of information processing can be useful in computer vision systems that are under similar computational constraints. To this aim, this project investigates the relative influence of simple bottom-up attention and more complicated top-down attention for the applications of object recognition and scene understanding. Bottom-up attention is formed from low-level features that attract our attention such as a red dot in a sea of blue dots. Top-down attention stems from higher level cognitive processing, such as detecting a face in the scene. Together these two factors can yield a more appropriate attention model for use in computer vision recognition tasks.Broader impacts of an EAPSI fellowship include providing the Fellow a first-hand research experience outside the U.S.; an introduction to the science, science policy, and scientific infrastructure of the respective location; and an orientation to the society, culture and language. These activities meet the NSF goal to educate for international collaborations early in the career of its scientists, engineers, and educators, thus ensuring a globally aware U.S. scientific workforce. Furthermore, the results of this research will be disseminated in a top computer vision conference, so that this research can find use in practical application areas such as automation, healthcare, and intelligent systems. The fellow is working with Chinese graduate and undergraduate students to improve their professional English, so that they will be more prepared for conferences.