no code implementations • 6 Feb 2024 • Nimrod Berman, Eitan Kosman, Dotan Di Castro, Omri Azencot
Graph generation is integral to various engineering and scientific disciplines.
no code implementations • 11 Sep 2023 • Ali Keysan, Andreas Look, Eitan Kosman, Gonca Gürsun, Jörg Wagner, Yu Yao, Barbara Rakitsch
In autonomous driving tasks, scene understanding is the first step towards predicting the future behavior of the surrounding traffic participants.
no code implementations • 4 Jul 2022 • Eitan Kosman, Dotan Di Castro
We propose a concise representation of videos that encode perceptually meaningful features into graphs.
no code implementations • 10 Nov 2021 • Eitan Kosman, Joel Oren, Dotan Di Castro
In this paper, we take a further step towards demystifying this phenomenon and propose a systematic method called Locality-Sensitive Pruning (LSP) for graph pruning based on Locality-Sensitive Hashing.
no code implementations • 27 Jul 2021 • Eitan Kosman, Dotan Di Castro
We examine the contribution of vision features, and find that a model fed with vision features achieves an error that is 56. 6% and 66. 9% of the error of a model that doesn't use those features, on the Udacity and Comma2k19 datasets respectively.