Zobrazeno 1 - 10
of 913
pro vyhledávání: '"Pippi P."'
Autor:
Beraldo, Dario, Pippi, Massimo
We apply methods of derived and non-commutative algebraic geometry to understand ramification phenomena on arithmetic schemes. As an application, we prove the Deligne-Milnor conjecture and, in the pure characteristic case, a generalization of Bloch c
Externí odkaz:
http://arxiv.org/abs/2410.02327
Diffusion models have become the State-of-the-Art for text-to-image generation, and increasing research effort has been dedicated to adapting the inference process of pretrained diffusion models to achieve zero-shot capabilities. An example is the ge
Externí odkaz:
http://arxiv.org/abs/2408.15660
Designs and artworks are ubiquitous across various creative fields, requiring graphic design skills and dedicated software to create compositions that include many graphical elements, such as logos, icons, symbols, and art scenes, which are integral
Externí odkaz:
http://arxiv.org/abs/2408.14826
Document Image Binarization is a well-known problem in Document Analysis and Computer Vision, although it is far from being solved. One of the main challenges of this task is that documents generally exhibit degradations and acquisition artifacts tha
Externí odkaz:
http://arxiv.org/abs/2404.17243
Autor:
Vanherle, Bram, Pippi, Vittorio, Cascianelli, Silvia, Michiels, Nick, Van Reeth, Frank, Cucchiara, Rita
Styled Handwritten Text Generation (HTG) has received significant attention in recent years, propelled by the success of learning-based solutions employing GANs, Transformers, and, preliminarily, Diffusion Models. Despite this surge in interest, ther
Externí odkaz:
http://arxiv.org/abs/2402.10798
Styled Handwritten Text Generation (Styled HTG) is an important task in document analysis, aiming to generate text images with the handwriting of given reference images. In recent years, there has been significant progress in the development of deep
Externí odkaz:
http://arxiv.org/abs/2310.20316
Recent advancements in Digital Document Restoration (DDR) have led to significant breakthroughs in analyzing highly damaged written artifacts. Among those, there has been an increasing interest in applying Artificial Intelligence techniques for virtu
Externí odkaz:
http://arxiv.org/abs/2308.05070
Recent advancements in Deep Learning-based Handwritten Text Recognition (HTR) have led to models with remarkable performance on both modern and historical manuscripts in large benchmark datasets. Nonetheless, those models struggle to obtain the same
Externí odkaz:
http://arxiv.org/abs/2305.02593
In this work, we explore massive pre-training on synthetic word images for enhancing the performance on four benchmark downstream handwriting analysis tasks. To this end, we build a large synthetic dataset of word images rendered in several handwriti
Externí odkaz:
http://arxiv.org/abs/2304.01842
Generating synthetic images of handwritten text in a writer-specific style is a challenging task, especially in the case of unseen styles and new words, and even more when these latter contain characters that are rarely encountered during training. W
Externí odkaz:
http://arxiv.org/abs/2303.15269