Zobrazeno 1 - 10
of 1 168
pro vyhledávání: '"Fischer, Andréas"'
This thesis investigates the effectiveness of SimCLR, a contrastive learning technique, in Greek letter recognition, focusing on the impact of various augmentation techniques. We pretrain the SimCLR backbone using the Alpub dataset (pretraining datas
Externí odkaz:
http://arxiv.org/abs/2409.10156
When dealing with general Lipschitzian optimization problems, there are many problem classes where standard constraint qualifications fail at local minimizers. In contrast to a constraint qualification, a problem qualification does not only rely on t
Externí odkaz:
http://arxiv.org/abs/2407.16422
Publikováno v:
Fifteenth International Conference on Computational Logics, Algebras, Programming, Tools, and Benchmarking (COMPUTATION TOOLS 2024), ISSN: 2308-4170
Managing the semantic quality of the categorization in large textual datasets, such as Wikipedia, presents significant challenges in terms of complexity and cost. In this paper, we propose leveraging transformer models to distill semantic information
Externí odkaz:
http://arxiv.org/abs/2404.16442
Autor:
Jungo, Michael, Vögtlin, Lars, Fakhari, Atefeh, Wegmann, Nathan, Ingold, Rolf, Fischer, Andreas, Scius-Bertrand, Anna
Publikováno v:
SOICT 2023: The 12th International Symposium on Information and Communication Technology
Handwriting recognition is a key technology for accessing the content of old manuscripts, helping to preserve cultural heritage. Deep learning shows an impressive performance in solving this task. However, to achieve its full potential, it requires a
Externí odkaz:
http://arxiv.org/abs/2312.09037
Publikováno v:
International Conference on Document Analysis and Recognition - ICDAR 2023, pp. 98-114. Cham: Springer Nature Switzerland
On-line handwritten character segmentation is often associated with handwriting recognition and even though recognition models include mechanisms to locate relevant positions during the recognition process, it is typically insufficient to produce a p
Externí odkaz:
http://arxiv.org/abs/2309.03072
Ambiguity is ubiquitous in natural language. Resolving ambiguous meanings is especially important in information retrieval tasks. While word embeddings carry semantic information, they fail to handle ambiguity well. Transformer models have been shown
Externí odkaz:
http://arxiv.org/abs/2307.13417
Autor:
Bettouche, Zineddine, Fischer, Andreas
Modern performance on several natural language processing (NLP) tasks has been enhanced thanks to the Transformer-based pre-trained language model BERT. We employ this concept to investigate a local publication database. Research papers are encoded a
Externí odkaz:
http://arxiv.org/abs/2306.09049
Autor:
Hollmer, Michael, Fischer, Andreas
In this paper the concept of a machine learning based hands-on detection algorithm is proposed. The hand detection is implemented on the hardware side using a capacitive method. A sensor mat in the steering wheel detects a change in capacity as soon
Externí odkaz:
http://arxiv.org/abs/2306.09044
Autor:
Bettouche, Zineddine, Fischer, Andreas
Publikováno v:
IARIA Journal on Advances in Software, ISSN: 1942-2628, vol. 15, pp. 141-151, 2022
The process of transforming a raster image into a vector representation is known as image tracing. This study looks into several processing methods that include high-pass filtering, autoencoding, and vectorization to extract an abstract representatio
Externí odkaz:
http://arxiv.org/abs/2306.09039
Autor:
Feldmann, Daniel, Oehme, Felix, von Germersheim, Lennart, Parras, Ruben Lopez, Fischer, Andreas, Avila, Marc
We present results from novel field, lab and computer studies, that pave the way towards non-invasive classification of localised surface defects on running wind turbine rotors using infrared thermography (IRT). In particular, we first parametrise th
Externí odkaz:
http://arxiv.org/abs/2302.05716