Zobrazeno 1 - 10
of 105
pro vyhledávání: '"Gunther Heidemann"'
Autor:
Leila Malihi, Gunther Heidemann
Publikováno v:
Applied System Innovation, Vol 7, Iss 4, p 56 (2024)
In recent years, model compression techniques have gained significant attention as a means to reduce the computational and memory requirements of deep neural networks. Knowledge distillation and pruning are two prominent approaches in this domain, ea
Externí odkaz:
https://doaj.org/article/0a398732660e4ec7a44511b8cce42c18
Autor:
Axel Schaffland, Gunther Heidemann
Publikováno v:
Heritage, Vol 5, Iss 4, Pp 4267-4305 (2022)
Repeat photography, the process of locating the camera position of an old photo and taking a new photo from this position, is utilized to protect our natural heritage, by measuring landscape changes between old and new image, and to conserve and reco
Externí odkaz:
https://doaj.org/article/327e06778b7340ed9c8cf63d3c15c19a
Publikováno v:
Information, Vol 15, Iss 2, p 114 (2024)
Self-supervised learning (SSL) has emerged as a promising paradigm for learning flexible speech representations from unlabeled data. By designing pretext tasks that exploit statistical regularities, SSL models can capture useful representations that
Externí odkaz:
https://doaj.org/article/aa7e2b91d7f14583a0a5a05ba9d425e0
Autor:
Leila Malihi, Gunther Heidemann
Publikováno v:
Big Data and Cognitive Computing, Vol 7, Iss 3, p 154 (2023)
Efficient model deployment is a key focus in deep learning. This has led to the exploration of methods such as knowledge distillation and network pruning to compress models and increase their performance. In this study, we investigate the potential s
Externí odkaz:
https://doaj.org/article/6a73d61954b74eac908d6f816b4ddb5d
Publikováno v:
Journal of Eye Movement Research, Vol 10, Iss 5 (2017)
With the increasing number of studies, where participants’ eye movements are tracked while watching videos, the volume of gaze data records is growing tremendously. Unfortunately, in most cases, such data are collected in separate files in custom-m
Externí odkaz:
https://doaj.org/article/5cc6aca5bc55488dadf06be0f5f0b460
Publikováno v:
Journal of Spatial Information Science, Iss 2, Pp 87-117 (2011)
Vast amounts of video data render manual video analysis useless while recent automatic video analytics techniques suffer from insufficient performance. To alleviate these issues, we present a scalable and reliable approach exploiting the visual analy
Externí odkaz:
https://doaj.org/article/ca913a18a1d84bcb9b3af1bbab4f410e
Publikováno v:
Journal of Spatial Information Science, Vol 2011, Iss 2, Pp 87-117 (1969)
Vast amounts of video data render manual video analysis useless while recent automatic video analytics techniques suffer from insufficient performance. To alleviate these issues, we present a scalable and reliable approach exploiting the visual analy
Externí odkaz:
https://doaj.org/article/6214938dd18a4ef883fbea73b724bfe8
Autor:
Leila Malihi, Ursula Hübner, Mats L. Richter, Maurice Moelleken, Mareike Przysucha, Dorothee Busch, Jan Heggemann, Guido Hafer, Stefan Wiemeyer, Gunther Heidemann, Joachim Dissemond, Cornelia Erfurt-Berge, Carlotta Barkhau, Achim Hendriks, Jens Hüsers
Publikováno v:
Caring is Sharing – Exploiting the Value in Data for Health and Innovation ISBN: 9781643683881
For artificial intelligence (AI) based systems to become clinically relevant, they must perform well. Machine Learning (ML) based AI systems require a large amount of labelled training data to achieve this level. In cases of a shortage of such large
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bad5c26d1ba8a4935d846f16d42d70cc
https://doi.org/10.3233/shti230311
https://doi.org/10.3233/shti230311
Autor:
Leila, Malihi, Jens, Hüsers, Mats L, Richter, Maurice, Moelleken, Mareike, Przysucha, Dorothee, Busch, Jan, Heggemann, Guido, Hafer, Stefan, Wiemeyer, Gunther, Heidemann, Joachim, Dissemond, Cornelia, Erfurt-Berge, Ursula, Hübner
Publikováno v:
Studies in health technology and informatics. 295
Chronic wounds are ulcerations of the skin that fail to heal because of an underlying condition such as diabetes mellitus or venous insufficiency. The timely identification of this condition is crucial for healing. However, this identification requir
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=pmid________::dc7e99643c8129928ad3637806fe1322
https://pubmed.ncbi.nlm.nih.gov/35773863
https://pubmed.ncbi.nlm.nih.gov/35773863
Autor:
Jens, Hüsers, Maurice, Moelleken, Mats L, Richter, Mareike, Przysucha, Leila, Malihi, Dorothee, Busch, Nina-Alexandra, Götz, Jan, Heggemann, Guido, Hafer, Stefan, Wiemeyer, Birgit, Babitsch, Gunther, Heidemann, Joachim, Dissemond, Cornelia, Erfurt-Berge, Ursula, Hübner
Publikováno v:
Studies in health technology and informatics. 294
Venous leg ulcers and diabetic foot ulcers are the most common chronic wounds. Their prevalence has been increasing significantly over the last years, consuming scarce care resources. This study aimed to explore the performance of detection and class
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=pmid________::c1eb8245d3f887eb356104c1c38a5446
https://pubmed.ncbi.nlm.nih.gov/35612017
https://pubmed.ncbi.nlm.nih.gov/35612017