no code implementations • IET Image Processing 2020 • Mohammadreza Riahi, Mohammad Eslami, Seyed Hamid Safavi, Farah Torkamani Azar
Experimental results on popular UCF11, Olympic Sports, and J-HMDB datasets show the superiority of the proposed KFDI approach compared to the DI in capturing long dynamics of videos for action recognition.
no code implementations • 26 Sep 2016 • Rui Liu, Hossein Nejati, Seyed Hamid Safavi, Ngai-Man Cheung
We propose an algorithm to uncover the intrinsic low-rank component of a high-dimensional, graph-smooth and grossly-corrupted dataset, under the situations that the underlying graph is unknown.