A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is
2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)
Action recognition based on human pose has witnessed increasing attention due to its robustness to changes in appearances, environments, and view-points. Despite associated progress, one remaining challenge has to do with occlusion in real-world videos that hinders the visibility of all joints. Such occlusion impedes representation of such scenes by models that have been trained on full-body pose data, obtained in laboratory conditions with specific sensors. To address this, as a firstdoi:10.1109/fg52635.2021.9667032 fatcat:i5lvlv2vmja4zexthcy27m6rjm