GOO 凝视对象预测数据集

GOO 全称 Gaze-on-Objects，是一个面向零售环境的凝视对象预测数据集。该数据集的目标是预测一个被人注视的物体的边界框。 GOO 由一个大的合成图像组（GOO Synth）和一个较小的真实图像子集（GOO-Real）组成，后者是人们在零售环境中看物体的图像。

GOO, whose full name is Gaze-on-Objects, is a gaze-based object prediction dataset designed for retail environments. The goal of this dataset is to predict the bounding box of the object that a person is gazing at. GOO consists of a large set of synthetic images (GOO Synth) and a smaller real-world image subset (GOO-Real), where the latter comprises images of people looking at objects in retail environments.

搜集汇总

背景与挑战

背景概述

GOO凝视对象预测数据集（Gaze-on-Objects）专注于零售环境，旨在预测被人注视物体的边界框。该数据集包含一个大型合成图像组（GOO Synth）和一个较小的真实图像子集（GOO-Real），适用于图像识别、目标跟踪等计算机视觉任务。