BibTex format

author = {Bin, Razali MH and Demiris, Y},
title = {Using eye-gaze to forecast human pose in everyday pick and place actions},
url = {},
year = {2022}

RIS format (EndNote, RefMan)

AB - Collaborative robots that operate alongside hu-mans require the ability to understand their intent and forecasttheir pose. Among the various indicators of intent, the eyegaze is particularly important as it signals action towards thegazed object. By observing a person’s gaze, one can effectivelypredict the object of interest and subsequently, forecast theperson’s pose. We leverage this and present a method thatforecasts the human pose using gaze information for everydaypick and place actions in a home environment. Our method firstattends to fixations to locate the coordinates of the object ofinterest before inputting said coordinates to a pose forecastingnetwork. Experiments on the MoGaze dataset show that ourgaze network lowers the errors of existing pose forecastingmethods and that incorporating prior in the form of textualinstructions further lowers the errors by a significant amount.Furthermore, the use of eye gaze now allows a simple multilayerperceptron network to directly forecast the keypose.
AU - Bin,Razali MH
AU - Demiris,Y
PY - 2022///
TI - Using eye-gaze to forecast human pose in everyday pick and place actions
UR -
ER -