Zobrazeno 1 - 10
of 740
pro vyhledávání: '"Jung, Steffen"'
Autor:
Gavrikov, Paul, Lukasik, Jovita, Jung, Steffen, Geirhos, Robert, Lamm, Bianca, Mirza, Muhammad Jehanzeb, Keuper, Margret, Keuper, Janis
Vision language models (VLMs) have drastically changed the computer vision model landscape in only a few years, opening an exciting array of new applications from zero-shot image classification, over to image captioning, and visual question answering
Externí odkaz:
http://arxiv.org/abs/2403.09193
Hand action recognition is essential. Communication, human-robot interactions, and gesture control are dependent on it. Skeleton-based action recognition traditionally includes hands, which belong to the classes which remain challenging to correctly
Externí odkaz:
http://arxiv.org/abs/2308.10557
Deep learning models have proven to be successful in a wide range of machine learning tasks. Yet, they are often highly sensitive to perturbations on the input data which can lead to incorrect decisions with high confidence, hampering their deploymen
Externí odkaz:
http://arxiv.org/abs/2306.06712
In recent years, optimization in the learned latent space of deep generative models has been successfully applied to black-box optimization problems such as drug design, image generation or neural architecture search. Existing models thereby leverage
Externí odkaz:
http://arxiv.org/abs/2306.06684
While neural networks allow highly accurate predictions in many tasks, their lack of robustness towards even slight input perturbations often hampers their deployment. Adversarial attacks such as the seminal projected gradient descent (PGD) offer an
Externí odkaz:
http://arxiv.org/abs/2302.02213
Autor:
Jung, Steffen, Keuper, Margret
The minimum cost multicut problem is the NP-hard/APX-hard combinatorial optimization problem of partitioning a real-valued edge-weighted graph such as to minimize the total cost of the partition. While graph convolutional neural networks (GNN) have p
Externí odkaz:
http://arxiv.org/abs/2204.01366
Over the last years, Convolutional Neural Networks (CNNs) have been the dominating neural architecture in a wide range of computer vision tasks. From an image and signal processing point of view, this success might be a bit surprising as the inherent
Externí odkaz:
http://arxiv.org/abs/2204.00491
The efficient, automated search for well-performing neural architectures (NAS) has drawn increasing attention in the recent past. Thereby, the predominant research objective is to reduce the necessity of costly evaluations of neural architectures whi
Externí odkaz:
http://arxiv.org/abs/2203.08734
The Minimum Cost Multicut Problem (MP) is a popular way for obtaining a graph decomposition by optimizing binary edge labels over edge costs. While the formulation of a MP from independently estimated costs per edge is highly flexible and intuitive,
Externí odkaz:
http://arxiv.org/abs/2112.05416
Autor:
Trzebanski, Sébastien, Kim, Jung-Seok, Larossi, Niss, Raanan, Ayala, Kancheva, Daliya, Bastos, Jonathan, Haddad, Montaser, Solomon, Aryeh, Sivan, Ehud, Aizik, Dan, Kralova, Jarmila Sekeresova, Gross-Vered, Mor, Boura-Halfon, Sigalit, Lapidot, Tsvee, Alon, Ronen, Movahedi, Kiavash, Jung, Steffen
Publikováno v:
In Immunity 11 June 2024 57(6):1225-1242