Zobrazeno 1 - 10
of 168
pro vyhledávání: '"Thierry Paquet"'
Publikováno v:
IEEE Access, Vol 11, Pp 136552-136564 (2023)
This paper introduces Selective Path Automatic Differentiation (SPAD), a novel approach to reducing memory consumption and mitigating overfitting in gradient-based models for embedded artificial intelligence. SPAD extends the existing Randomized Auto
Externí odkaz:
https://doaj.org/article/c610ebb085114e6bbf333794aa21b613
Publikováno v:
ELCVIA Electronic Letters on Computer Vision and Image Analysis, Vol 5, Iss 2 (2005)
In this paper, we show that both the writer identification and the writer verification tasks can be carried out using local features such as graphemes extracted from the segmentation of cursive handwriting. We thus enlarge the scope of the possible u
Externí odkaz:
https://doaj.org/article/27f0057076f240bca51a9d726f5fbd6d
Publikováno v:
Pattern Recognition Letters. 166:31-37
Deep neural networks are becoming increasingly powerful and large and always require more labelled data to be trained. However, since annotating data is time-consuming, it is now necessary to develop systems that show good performance while learning
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 45:508-524
Unconstrained handwritten text recognition remains challenging for computer vision systems. Paragraph text recognition is traditionally achieved by two models: the first one for line segmentation and the second one for text line recognition. We propo
Publikováno v:
International Journal on Document Analysis and Recognition (IJDAR). 25:95-114
Text line segmentation is one of the key steps in historical document understanding. It is challenging due to the variety of fonts, contents, writing styles and the quality of documents that have degraded through the years. In this paper, we address
Unconstrained handwritten text recognition is a challenging computer vision task. It is traditionally handled by a two-step approach, combining line segmentation followed by text line recognition. For the first time, we propose an end-to-end segmenta
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::52ae5d2944f15d3f63b42ad1b18be4dc
Autor:
Sébastien Adam, Jan Annaert, Frans Buelens, Coüasnon, Bertrand B., Boris Cule, Amaury de Vicq, Camille Guerry, Pierre-Cyrille Hautcoeur, Thierry Paquet, Andres Rojas Camacho, Iwan Le Floch, Aurélie Lemaitre, Pantelis Karapanagiotis, Johan Poukens, Angelo Riva
Publikováno v:
Methodological Advances in the Extraction and Analysis of Historical Data
Methodological Advances in the Extraction and Analysis of Historical Data, Kellogg School of Management-Northwestern University, Dec 2021, Chicago/Virtual, United States
HAL
Methodological Advances in the Extraction and Analysis of Historical Data, Kellogg School of Management-Northwestern University, Dec 2021, Chicago/Virtual, United States
HAL
International audience This paper reports results from the design phase of EurHisFirm. Its goal is to integrate isolated and badly accessible financial data sets on 19 th and 20 th century European companies so that users can query the data as if the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::d737e0319f3943ff2cc88c570924f89d
https://hal.science/hal-03828381
https://hal.science/hal-03828381
Publikováno v:
International Conference on Document Analysis and Recognition
International Conference on Document Analysis and Recognition, pp.70-84, 2021, ⟨10.1007/978-3-030-86334-0_5⟩
Document Analysis and Recognition – ICDAR 2021 ISBN: 9783030863333
ICDAR (3)
International Conference on Document Analysis and Recognition, pp.70-84, 2021, ⟨10.1007/978-3-030-86334-0_5⟩
Document Analysis and Recognition – ICDAR 2021 ISBN: 9783030863333
ICDAR (3)
Unconstrained handwriting recognition is an essential task in document analysis. It is usually carried out in two steps. First, the document is segmented into text lines. Second, an Optical Character Recognition model is applied on these line images.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::34521b859cd6ab8c4cd52a95bf567732
https://hal.archives-ouvertes.fr/hal-03342274
https://hal.archives-ouvertes.fr/hal-03342274
Publikováno v:
Pattern Recognition Letters
Pattern Recognition Letters, Elsevier, 2019, 121, pp.68-76. ⟨10.1016/j.patrec.2018.07.027⟩
Pattern Recognition Letters, Elsevier, 2019, 121, pp.68-76. ⟨10.1016/j.patrec.2018.07.027⟩
We address the design of a unified multilingual system for handwriting recognition. Most of multi- lingual systems rests on specialized models that are trained on a single language and one of them is selected at test time. While some recognition syst