Zobrazeno 1 - 10
of 673
pro vyhledávání: '"Pižurica, A."'
Deep subspace clustering methods are now prominent in clustering, typically using fully connected networks and a self-representation loss function. However, these methods often struggle with overfitting and lack interpretability. In this paper, we ex
Externí odkaz:
http://arxiv.org/abs/2404.07112
Automated mark localization in scatter images, greatly helpful for discovering knowledge and understanding enormous document images and reasoning in visual question answering AI systems, is a highly challenging problem because of the ubiquity of over
Externí odkaz:
http://arxiv.org/abs/2312.11146
Autor:
de la Fuente, Jesus, Serrano, Guillermo, Veleiro, Uxía, Casals, Mikel, Vera, Laura, Pizurica, Marija, Pineda-Lucena, Antonio, Ochoa, Idoia, Vicent, Silve, Gevaert, Olivier, Hernaez, Mikel
Drug-target interaction (DTI) prediction is a challenging, albeit essential task in drug repurposing. Learning on graph models have drawn special attention as they can significantly reduce drug repurposing costs and time commitment. However, many cur
Externí odkaz:
http://arxiv.org/abs/2311.12670
One of the largest problems in medical image processing is the lack of annotated data. Labeling medical images often requires highly trained experts and can be a time-consuming process. In this paper, we evaluate a method of reducing the need for lab
Externí odkaz:
http://arxiv.org/abs/2206.00344
Autor:
Van den Borre, Ide, Peiffer, Matthias, Huysentruyt, Roel, Huyghe, Manu, Vervelghe, Jean, Pizurica, Aleksandra, Audenaert, Emmanuel A., Burssens, Arne
Publikováno v:
In Gait & Posture September 2024 113:67-74
Publikováno v:
In Computer Methods and Programs in Biomedicine March 2024 245
Conditional Variational Auto Encoders (VAE) are gathering significant attention as an Explainable Artificial Intelligence (XAI) tool. The codes in the latent space provide a theoretically sound way to produce counterfactuals, i.e. alterations resulti
Externí odkaz:
http://arxiv.org/abs/2102.00854
Autor:
Nadisic, Nicolas, Arhant, Yoann, Vyncke, Niels, Verplancke, Sebastiaan, Lazendić, Srdan, Pižurica, Aleksandra
Publikováno v:
In Procedia Structural Integrity 2024 64:2173-2180
Autor:
Carrillo-Perez, Francisco, Pizurica, Marija, Ozawa, Michael G., Vogel, Hannes, West, Robert B., Kong, Christina S., Herrera, Luis Javier, Shen, Jeanne, Gevaert, Olivier
Publikováno v:
In Cell Reports Methods 28 August 2023 3(8)
Publikováno v:
Sensors, Vol 24, Iss 5, p 1414 (2024)
Generative models have the potential to revolutionize 3D extended reality. A primary obstacle is that augmented and virtual reality need real-time computing. Current state-of-the-art point cloud random generation methods are not fast enough for these
Externí odkaz:
https://doaj.org/article/171e3d4821da4f33a3f489c9606a8e2f