In this section
@inproceedings{Bin:2022:10.1109/ICASSP43922.2022.9747710,
author = {Bin, Razali MH and Demiris, Y},
doi = {10.1109/ICASSP43922.2022.9747710},
pages = {3488--3492},
publisher = {IEEE},
title = {Using a single input to forecast human action keystates in everyday pick and place actions},
url = {http://dx.doi.org/10.1109/ICASSP43922.2022.9747710},
year = {2022}
}
TY - CPAPER
AB - We define action keystates as the start or end of an actionthat contains information such as the human pose and time.Existing methods that forecast the human pose use recurrentnetworks that input and output a sequence of poses. In this pa-per, we present a method tailored for everyday pick and placeactions where the object of interest is known. In contrast toexisting methods, ours uses an input from a single timestep todirectly forecast (i) the key pose the instant the pick or placeaction is performed and (ii) the time it takes to get to the pre-dicted key pose. Experimental results show that our methodoutperforms the state-of-the-art for key pose forecasting andis comparable for time forecasting while running at least anorder of magnitude faster. Further ablative studies reveal thesignificance of the object of interest in enabling the total num-ber of parameters across all existing methods to be reduced byat least 90% without any degradation in performance.
AU - Bin,Razali MH
AU - Demiris,Y
DO - 10.1109/ICASSP43922.2022.9747710
EP - 3492
PB - IEEE
PY - 2022///
SP - 3488
TI - Using a single input to forecast human action keystates in everyday pick and place actions
UR - http://dx.doi.org/10.1109/ICASSP43922.2022.9747710
UR - https://ieeexplore.ieee.org/abstract/document/9747710
UR - http://hdl.handle.net/10044/1/95433
ER -
