no code implementations • 24 Feb 2021 • Flavio Santos, Cleber Zanchettin, Leonardo Matos, Paulo Novais
The results show that all methods achieve similar performance at the ending of training, but when combining ADA with GradCam, the U-Net model presented an impressive fast convergence.
no code implementations • 12 Jul 2020 • Michel Meneses, Leonardo Matos, Bruno Prado, André de Carvalho, Hendrik Macedo
With the recent advances in the object detection research field, tracking-by-detection has become the leading paradigm adopted by multi-object tracking algorithms.