1 code implementation • 2 Apr 2020 • Ehsan Yaghoubi, Diana Borza, João Neves, Aruna Kumar, Hugo Proença
The automatic characterization of pedestrians in surveillance footage is a tough challenge, particularly when the data is extremely diverse with cluttered backgrounds, and subjects are captured from varying distances, under multiple poses, with partial occlusion.
1 code implementation • 30 Jan 2020 • Ehsan Yaghoubi, Diana Borza, Aruna Kumar, Hugo Proença
The \emph{receptive fields} of deep learning classification models determine the regions of the input data that have the most significance for providing correct decisions.