Zobrazeno 1 - 10
of 1 876
pro vyhledávání: '"Caye A"'
Autor:
Ke, Bingxin, Obukhov, Anton, Huang, Shengyu, Metzger, Nando, Daudt, Rodrigo Caye, Schindler, Konrad
Monocular depth estimation is a fundamental computer vision task. Recovering 3D depth from a single image is geometrically ill-posed and requires scene understanding, so it is not surprising that the rise of deep learning has led to a breakthrough. T
Externí odkaz:
http://arxiv.org/abs/2312.02145
Recent approaches for arbitrary-scale single image super-resolution (ASSR) have used local neural fields to represent continuous signals that can be sampled at arbitrary rates. However, the point-wise query of the neural field does not naturally matc
Externí odkaz:
http://arxiv.org/abs/2311.17643
Detailed population maps play an important role in diverse fields ranging from humanitarian action to urban planning. Generating such maps in a timely and scalable manner presents a challenge, especially in data-scarce regions. To address it we have
Externí odkaz:
http://arxiv.org/abs/2311.14006
Autor:
E. D. Hafner, T. Kontogianni, R. Caye Daudt, L. Oberson, J. D. Wegner, K. Schindler, Y. Bühler
Publikováno v:
The Cryosphere, Vol 18, Pp 3807-3823 (2024)
For many safety-related applications such as hazard mapping or road management, well-documented avalanche events are crucial. Nowadays, despite the variety of research directions, the available data are mostly restricted to isolated locations where t
Externí odkaz:
https://doaj.org/article/adc2d12306cc42d484508b5046d0f752
Autor:
Jair de Jesus Mari, Flávio Kapczinski, André Russowsky Brunoni, Ary Gadelha, Daniel Prates-Baldez, Eurípedes Constantino Miguel, Fulvio A. Scorza, Arthur Caye, Laiana A. Quagliato, Raquel B. De Boni, Giovanni Salum, Antonio E. Nardi
Publikováno v:
Brazilian Journal of Psychiatry, Vol 46 (2024)
This is the second part of the Brazilian S20 mental health report. The mental health working group is dedicated to leveraging scientific insights to foster innovation and propose actionable recommendations for implementation in Brazil and participati
Externí odkaz:
https://doaj.org/article/8028afe9a8944a799ddabba65880340d
Performing super-resolution of a depth image using the guidance from an RGB image is a problem that concerns several fields, such as robotics, medical imaging, and remote sensing. While deep learning methods have achieved good results in this problem
Externí odkaz:
http://arxiv.org/abs/2211.11592
Autor:
Kalischek, Nikolai, Lang, Nico, Renier, Cécile, Daudt, Rodrigo Caye, Addoah, Thomas, Thompson, William, Blaser-Hart, Wilma J., Garrett, Rachael, Schindler, Konrad, Wegner, Jan D.
C\^ote d'Ivoire and Ghana, the world's largest producers of cocoa, account for two thirds of the global cocoa production. In both countries, cocoa is the primary perennial crop, providing income to almost two million farmers. Yet precise maps of coco
Externí odkaz:
http://arxiv.org/abs/2206.06119
Autor:
Silva, Warley Almeida, Bobbio, Federico, Caye, Flore, Liu, Defeng, Pepin, Justine, Perreault-Lafleur, Carl, St-Arnaud, William
We present a solver for Mixed Integer Programs (MIP) developed for the MIP competition 2022. Given the 10 minutes bound on the computational time established by the rules of the competition, our method focuses on finding a feasible solution and impro
Externí odkaz:
http://arxiv.org/abs/2206.01857
Autor:
Rodríguez, Andrés C., D'Aronco, Stefano, Daudt, Rodrigo Caye, Wegner, Jan D., Schindler, Konrad
We exploit field guides to learn bird species recognition, in particular zero-shot recognition of unseen species. Illustrations contained in field guides deliberately focus on discriminative properties of each species, and can serve as side informati
Externí odkaz:
http://arxiv.org/abs/2206.01466
Autor:
Turkoglu, Mehmet Ozgur, Becker, Alexander, Gündüz, Hüseyin Anil, Rezaei, Mina, Bischl, Bernd, Daudt, Rodrigo Caye, D'Aronco, Stefano, Wegner, Jan Dirk, Schindler, Konrad
The ability to estimate epistemic uncertainty is often crucial when deploying machine learning in the real world, but modern methods often produce overconfident, uncalibrated uncertainty predictions. A common approach to quantify epistemic uncertaint
Externí odkaz:
http://arxiv.org/abs/2206.00050