ServiceNow/ui-vision
收藏官方服务:
资源简介:
UI-Vision是一个面向桌面环境的图形用户界面(GUI)视觉感知和交互的综合性评估基准。它提供了83个软件应用程序的人类演示的高质量注释,包括边界框、UI标签和动作轨迹,用于离线、细粒度的计算机使用代理评估。
UI-Vision is a comprehensive benchmark for visual perception and interaction in desktop-centric Graphical User Interfaces (GUIs). It provides high-quality annotations of human demonstrations, including bounding boxes, UI labels, and action trajectories across 83 software applications for offline, fine-grained evaluation of computer use agents.
提供机构:
ServiceNow


