LISA: Language-guided Interference-aware Spatial-Frequency Attention for Driver Gaze Estimation
LISA: 语言引导的干扰感知空间-频率注意力用于驾驶员视线估计
机构 * School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications(北京邮电大学计算机科学学院(国家级试点软件工程学院)) ; Key Laboratory of Trustworthy Distributed Computing and Service (BUPT), Ministry of Education(教育部可信分布式计算与服务重点实验室(BUPT)) ; School of Electrical Engineering, Guangxi University(广西大学电气工程学院) ; Zhejiang University(浙江大学)
专题命中 代码评测 :repository(abstract)
AI总结 提出LISA框架,结合频域先验与视觉语言知识,通过双域融合机制和训练时解耦策略,实现鲁棒的驾驶员视线估计,在遮挡和光照变化下达到最优性能。
Comments 9 pages, 5 figures, 3 tables