Background: The Face-to-Face Still-Face (FFSF) task is a validated and commonly used observational measure of mother-infant socio-emotional interactions. With the ascendence of deep learning-based facial emotion recognition, it is possible that common complex tasks, such as the coding of FFSF videos, could be coded with a high degree of accuracy by deep neural networks (DNNs). The primary objective of this study was to test the accuracy of four DNN image classification models against the coding of infant engagement conducted by two trained independent manual raters.
View Article and Find Full Text PDFObjective: This study examined the impact of treating postpartum depression (PPD) with cognitive-behavioral therapy (CBT) on mother and infant behavior on the face-to-face still-face (FFSF) paradigm.
Methods: Data from 68 mothers and their infants, 35 women with PPD within 12 months of delivery, and 33 healthy control dyads matched on infant age, sex and familial socioeconomic status were examined. Women with PPD received nine weeks of group CBT and were compared with healthy control dyads with at three timepoints on changes in mother-infant performance on the FFSF.