no code implementations • 21 Jul 2019 • João Antunes, Pedro Abreu, Alexandre Bernardino, Asim Smailagic, Daniel Siewiorek
Our method, using fovea attention filtering and our generalized binary loss, achieves a relative video mAP improvement of 20% over the two-stream baseline in AVA, and is competitive with the state-of-the-art in the UCF101-24.
no code implementations • 26 Mar 2019 • João Antunes, Alexandre Bernardino, Asim Smailagic, Daniel Siewiorek
In this paper we propose an improved method for transfer learning that takes into account the balance between target and source data.