Zobrazeno 1 - 10
of 8 870
pro vyhledávání: '"A. Blumenstein"'
Tackling non-IID data is an open challenge in federated learning research. Existing FL methods, including robust FL and personalized FL, are designed to improve model performance without consideration of interpreting non-IID across clients. This pape
Externí odkaz:
http://arxiv.org/abs/2406.19631
Recently, foundation models, particularly large language models (LLMs), have demonstrated an impressive ability to adapt to various tasks by fine-tuning large amounts of instruction data. Notably, federated foundation models emerge as a privacy prese
Externí odkaz:
http://arxiv.org/abs/2403.19211
Autor:
Das, Alloy, Biswas, Sanket, Roy, Prasun, Ghosh, Subhankar, Pal, Umapada, Blumenstein, Michael, Lladós, Josep, Bhattacharya, Saumik
Scene Text Editing (STE) is a challenging research problem, that primarily aims towards modifying existing texts in an image while preserving the background and the font style of the original text. Despite its utility in numerous real-world applicati
Externí odkaz:
http://arxiv.org/abs/2308.02905
Autor:
D. S. Ivanov, V. P. Lipp, A. Blumenstein, V. P. Veiko, Y. B. Yakovlev, V. V. Roddatis, M. E. Carcia, B. Rethfeld, J. Ihlemann, P. Simon
Publikováno v:
Naučno-tehničeskij Vestnik Informacionnyh Tehnologij, Mehaniki i Optiki, Vol 15, Iss 6, Pp 984-999 (2015)
Subject of Study. The mechanism of surface restructuring by ultrashort laser pulses involves a lot of fast, non-equilibrium, and interrelated processes while the solid is in a transient state. As a result, the analysis of the experimental data cannot
Externí odkaz:
https://doaj.org/article/2a30f25a617f40da952261b7f472a600
Handling various objects with different colors is a significant challenge for image colorization techniques. Thus, for complex real-world scenes, the existing image colorization algorithms often fail to maintain color consistency. In this work, we at
Externí odkaz:
http://arxiv.org/abs/2304.11993
Autor:
Krämer, Larissa1 (AUTHOR) larissa.kraemer@tu-dortmund.de, Stuckmann-Blumenstein, Patrick2 (AUTHOR), Kaiser, Pascal1 (AUTHOR), Henke, Michael2 (AUTHOR), Roidl, Moritz1 (AUTHOR), Kirchheim, Alice1 (AUTHOR)
Publikováno v:
International Journal of Production Research. Nov2024, p1-27. 27p. 9 Illustrations.
We propose a data-driven approach for context-aware person image generation. Specifically, we attempt to generate a person image such that the synthesized instance can blend into a complex scene. In our method, the position, scale, and appearance of
Externí odkaz:
http://arxiv.org/abs/2302.14728
Image colorization is a well-known problem in computer vision. However, due to the ill-posed nature of the task, image colorization is inherently challenging. Though several attempts have been made by researchers to make the colorization pipeline aut
Externí odkaz:
http://arxiv.org/abs/2208.02843
In computer vision, human pose synthesis and transfer deal with probabilistic image generation of a person in a previously unseen pose from an already available observation of that person. Though researchers have recently proposed several methods to
Externí odkaz:
http://arxiv.org/abs/2207.11718
Person image generation is an intriguing yet challenging problem. However, this task becomes even more difficult under constrained situations. In this work, we propose a novel pipeline to generate and insert contextually relevant person images into a
Externí odkaz:
http://arxiv.org/abs/2206.02717