Zobrazeno 1 - 10
of 9 790
pro vyhledávání: '"P, Gottschalk"'
Detecting road obstacles is essential for autonomous vehicles to navigate dynamic and complex traffic environments safely. Current road obstacle detection methods typically assign a score to each pixel and apply a threshold to generate final predicti
Externí odkaz:
http://arxiv.org/abs/2412.05707
Numerical simulations of turbulent flows present significant challenges in fluid dynamics due to their complexity and high computational cost. High resolution techniques such as Direct Numerical Simulation (DNS) and Large Eddy Simulation (LES) are ge
Externí odkaz:
http://arxiv.org/abs/2411.16417
Despite the recent progress in deep learning based computer vision, domain shifts are still one of the major challenges. Semantic segmentation for autonomous driving faces a wide range of domain shifts, e.g. caused by changing weather conditions, new
Externí odkaz:
http://arxiv.org/abs/2411.16407
Autor:
Schestakov, Stefan, Gottschalk, Simon
Trajectory representation learning is a fundamental task for applications in fields including smart city, and urban planning, as it facilitates the utilization of trajectory data (e.g., vehicle movements) for various downstream applications, such as
Externí odkaz:
http://arxiv.org/abs/2411.14014
Deep neural networks have achieved remarkable success in diverse applications, prompting the need for a solid theoretical foundation. Recent research has identified the minimal width $\max\{2,d_x,d_y\}$ required for neural networks with input dimensi
Externí odkaz:
http://arxiv.org/abs/2411.08735
Autor:
Afzali, Amirabbas, Khodabandeh, Borna, Rasekh, Ali, JafariNodeh, Mahyar, kazemi, Sepehr, Gottschalk, Simon
Contrastive learning models have demonstrated impressive abilities to capture semantic similarities by aligning representations in the embedding space. However, their performance can be limited by the quality of the training data and its inherent bia
Externí odkaz:
http://arxiv.org/abs/2411.08923
Autor:
Sao, Ashutosh, Gottschalk, Simon
Publikováno v:
27th European Conference on Artificial Intelligence (ECAI) 2024
Accurate spatio-temporal prediction is crucial for the sustainable development of smart cities. However, current approaches often struggle to capture important spatio-temporal relationships, particularly overlooking global relations among distant cit
Externí odkaz:
http://arxiv.org/abs/2411.06836
Developing a foundation model for time series forecasting across diverse domains has attracted significant attention in recent years. Existing works typically assume regularly sampled, well-structured data, limiting their applicability to more genera
Externí odkaz:
http://arxiv.org/abs/2410.23160
In recent years, a body of works has emerged, studying shape and texture biases of off-the-shelf pre-trained deep neural networks (DNN) for image classification. These works study how much a trained DNN relies on image cues, predominantly shape and t
Externí odkaz:
http://arxiv.org/abs/2410.14878
Autor:
Gottschalk, Jonas, Stellmer, Simon
Experiments in the field of quantum optics often require very low concentrations of dust particles in the laboratory, but the complexity of working routines precludes operation within a proper clean room. Research teams have established a multitude o
Externí odkaz:
http://arxiv.org/abs/2409.18325