Single Domain Generalization (SDG) tackles the problem of training a mod...
The performance of modern object detectors drops when the test distribut...
Multi-view approaches to people-tracking have the potential to better ha...
Data augmentation has proven its usefulness to improve model generalizat...
Several tasks in machine learning are evaluated using non-differentiable...
Humans share a strong tendency to memorize/forget some of the visual
inf...
Several works have proposed to learn a two-path neural network that maps...