HuTics Dataset

The authors created HuTics: Human Deictic Gestures Dataset, consisting of 2040 images collected from 170 people that include various deictic gestures and objects with segmentation mask annotations. The technical evaluation shows that their object highlights can achieve the accuracy of 0.718 (mean Intersection over Union; 𝑚𝐼𝑜𝑈) and can run at 28.3 fps. It covers four kinds of deictic gestures to objects: exhibit, pointing, present and touch.

作者构建了HuTics：人类指示性手势数据集，该数据集包含从170人处收集的2040张图片，涵盖了多种指示性手势及带有分割掩码标注的物体。技术评估表明，其物体高亮功能能够达到0.718（平均交并比；𝑚𝐼𝑜𝑈）的准确度，且运行速度可达28.3帧每秒。该数据集覆盖了四种指向物体的指示性手势：展示、指向、呈现和触摸。