GOO: A Dataset for Gaze Object Prediction in Retail Environments

TL;DR

This paper introduces GOO, a new dataset for gaze object prediction in retail environments, enabling models to predict object boundaries rather than just gaze points, advancing gaze estimation research.

Contribution

The paper presents the GOO dataset with synthetic and real images for gaze object prediction, and establishes baseline evaluations using state-of-the-art models.

Findings

Established baseline performance on GOO dataset

Demonstrated domain adaptation capabilities

Provided a new benchmark for gaze object prediction

Abstract

One of the most fundamental and information-laden actions humans do is to look at objects. However, a survey of current works reveals that existing gaze-related datasets annotate only the pixel being looked at, and not the boundaries of a specific object of interest. This lack of object annotation presents an opportunity for further advancing gaze estimation research. To this end, we present a challenging new task called gaze object prediction, where the goal is to predict a bounding box for a person's gazed-at object. To train and evaluate gaze networks on this task, we present the Gaze On Objects (GOO) dataset. GOO is composed of a large set of synthetic images (GOO Synth) supplemented by a smaller subset of real images (GOO-Real) of people looking at objects in a retail environment. Our work establishes extensive baselines on GOO by re-implementing and evaluating selected state-of-the art models on the task of gaze following and domain adaptation. Code is available on github.