An asynchronous, hands-off workflow for looking time experiments with infants.

The study of infant gaze has long been a key tool for understanding the developing mind. However, labor-intensive data collection and processing limit the speed at which this understanding can be advanced. Here, we demonstrate an asynchronous workflow for conducting violation-of-expectation (VoE) experiments, which is fully "hands-off" for the experimenter. We first replicate four classic VoE experiments in a synchronous online setting, and show that VoE can generate highly replicable effects through remote testing. We then confirm the accuracy of a state-of-the-art gaze annotation software, iCatcher+ in a new setting. Third, we train parents to control the experiment flow based on the infant's gaze. Combining all three innovations, we then conduct an asynchronous automated infant-contingent VoE experiment. The hands-off workflow successfully replicates a classic VoE effect: infants look longer at inefficient actions than efficient ones. We compare the resulting effect size and statistical power to the same study run in-lab and synchronously via Zoom. The hands-off workflow significantly reduces the marginal cost and time per participant, enabling larger sample sizes. By enhancing the reproducibility and robustness of findings relying on infant looking, this workflow could help support a cumulative science of infant cognition. Tools to implement the workflow are openly available. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

iCatcher+: Robust and Automated Annotation of Infants' and Young Children's Gaze Behavior From Videos Collected in Laboratory, Field, and Online Studies.

Technological advances in psychological research have enabled large-scale studies of human behavior and streamlined pipelines for automatic processing of data. However, studies of infants and children have not fully reaped these benefits because the behaviors of interest, such as gaze duration and direction, still have to be extracted from video through a laborious process of manual annotation, even when these data are collected online. Recent advances in computer vision raise the possibility of automated annotation of these video data. In this article, we built on a system for automatic gaze annotation in young children, iCatcher, by engineering improvements and then training and testing the system (referred to hereafter as iCatcher+) on three data sets with substantial video and participant variability (214 videos collected in U.S. lab and field sites, 143 videos collected in Senegal field sites, and 265 videos collected via webcams in homes; participant age range = 4 months-3.5 years). When trained on each of these data sets, iCatcher+ performed with near human-level accuracy on held-out videos on distinguishing "LEFT" versus "RIGHT" and "ON" versus "OFF" looking behavior across all data sets. This high performance was achieved at the level of individual frames, experimental trials, and study videos; held across participant demographics (e.g., age, race/ethnicity), participant behavior (e.g., movement, head position), and video characteristics (e.g., luminance); and generalized to a fourth, entirely held-out online data set. We close by discussing next steps required to fully automate the life cycle of online infant and child behavioral studies, representing a key step toward enabling robust and high-throughput developmental research.