CRI: II-New: Cognitive Mechanisms and Computational Modeling of Gaze Control During Scene Free Viewing, Visual Search, and Daily Tasks

这个项目是为了在中佛罗里达大学建立一个研究视觉注意力及其应用的基础设施。该基础设施还将使人们能够对视觉科学中的高级视觉识别问题进行更大规模的调查。固定和便携式眼球跟踪器的基础设施将被大学的几个教职员工和研究人员使用(例如，计算机科学、工程和计算机工程、心理学、生物医学工程和UCF模拟与培训研究所)，以研究人类的感知、认知、学习和运动控制，以及探索在活动识别、监视和数据汇总方面的应用。这个基础设施的核心目标是利用凝视和眼球跟踪技术从行为、神经生理学和计算角度理解注意机制，并探索其在计算机视觉和心理学的广泛问题中的应用。利用基础设施的团队拥有互补的专业知识，以解决涵盖计算机视觉、机器学习、人类视觉、成像和心理学的研究。特别是，这个基础设施将被用来探索当前的注意力模型在哪些方面失败了，如何弥补它们，并发现吸引目光的新线索。这种方法是利用机器学习和计算机视觉技术进行的认知和计算研究的结合。作为该计划的一部分，将构建新的大规模眼动数据集和基准。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

This project is to build an infrastructure to study visual attention and its applications at the University of Central Florida. The infrastructure will also enable larger-scale inquiries into high-level visual recognition problems in the vision sciences. The infrastructure of fixed and portable eye trackers will be used by several faculty and researchers across the University (e.g., Computer Science, Engineering and Computer Engineering, Psychology, Biomedical engineering and UCF Institute for Simulation and Training) to study human perception, cognition, learning, and motor control, as well as exploring applications in activity recognition, surveillance, and data summarization. The core goal of this infrastructure is to utilize gaze and eye tracking technology to understand mechanisms of attention from behavioral, neurophysiological, and computational perspectives and explore its applications in a wide range of problems in computer vision and psychology. The team utilizing the infrastructure has complementary expertise to address research encompassing computer vision, machine learning, human vision, imaging, and psychology. In particular, this infrastructure will be used to explore in what ways current attention models fail, how to remedy them, and discover new cues that attract gaze. The approach is a combination of cognitive and computational studies utilizing machine learning and computer vision techniques. New large-scale eye movement datasets and benchmarks will be constructed as part of this proposal.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.