no code implementations • 5 Jun 2024 • Mona Ahmadian, Frank Guerin, Andrew Gilbert
Our goal is to achieve a more semantic video representation by leveraging the text related to the video content during the pretraining in a fully self-supervised manner.
1 code implementation • 23 Aug 2023 • Mona Ahmadian, Frank Guerin, Andrew Gilbert
Despite the importance of motion in supervised learning techniques for action recognition, SSL methods often do not explicitly consider motion information in videos.
1 code implementation • 5 Mar 2023 • Amir Shirian, Mona Ahmadian, Krishna Somandepalli, Tanaya Guha
Heterogeneous graphs provide a compact, efficient, and scalable way to model data involving multiple disparate modalities.