Estimating Motion Codes from Demonstration Videos

TL;DR – This work uses the features from the motion taxonomy to improve action recognition on egocentric videos from the EPIC-KITCHENS dataset. This is done by integrating motion code detection for action sequences.

January 2021 · Maxat Alibayev, David Paulius, Yu Sun

Long Activity Video Understanding using Functional Object-Oriented Network

TL;DR – This work leverages functional object-oriented networks and deep learning for video understanding. In addition, with the deep network framework, we jointly recognize object and action types, which can then be used for constructing new FOON structures.

December 2018 · Ahmad Babaeian Jelodar, David Paulius, Yu Sun