Sfoglia per Soggetto "Pose information"
Items 1-2 di 2
-
An adversarial semi-supervised approach for action recognition from pose information
(2020)The collection of video data for action recognition is very susceptible to measurement bias; the equipment used, camera angle and environmental conditions are all factors that majorly affect the distribution of the collected ... -
SPATIO-TEMPORAL GRAPH CONVOLUTIONAL NETWORKS FOR CONTINUOUS SIGN LANGUAGE RECOGNITION
(2022)We address the challenging problem of continuous sign language recognition (CSLR) from RGB videos, proposing a novel deep-learning framework that employs spatio-temporal graph convolutional networks (ST-GCNs), which operate ...