no code implementations • 30 Oct 2022 • Igor Vozniak, Philipp Mueller, Lorena Hell, Nils Lipp, Ahmed Abouelazm, Christian Mueller
In this paper, we present Context-SalNET, a novel encoder-decoder architecture that explicitly addresses three key challenges of visual attention prediction in pedestrians: First, Context-SalNET explicitly models the context factors urgency and safety preference in the latent space of the encoder-decoder model.
no code implementations • 27 Oct 2021 • Sai Shyam Chanduri, Zeeshan Khan Suri, Igor Vozniak, Christian Müller
Recent advances in monocular depth estimation have shown that gaining such knowledge from a single camera input is possible by training deep neural networks to predict inverse depth and pose, without the necessity of ground truth data.