Zobrazeno 1 - 10
of 157
pro vyhledávání: '"Iuri Frosio"'
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031250811
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8c91cc6a7353cfa0c56b4e64cbd765ee
https://doi.org/10.1007/978-3-031-25082-8_6
https://doi.org/10.1007/978-3-031-25082-8_6
Autor:
Jan Kautz, Iuri Frosio
Publikováno v:
IEEE Transactions on Image Processing. 28:723-738
Non-local-means image denoising is based on processing a set of neighbors for a given reference patch. few nearest neighbors (NN) can be used to limit the computational burden of the algorithm. Resorting to a toy problem, we show analytically that sa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b897f430c71311f60b0637da376a75e1
https://doi.org/10.1109/tip.2018.2869685
https://doi.org/10.1109/tip.2018.2869685
Game publishers and anti-cheat companies have been unsuccessful in blocking cheating in online gaming. We propose a novel, vision-based approach that captures the final state of the frame buffer and detects illicit overlays. To this aim, we train and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e87da28f29a4bfc9c959bce0453e5198
http://arxiv.org/abs/2103.10031
http://arxiv.org/abs/2103.10031
Autor:
Stephen W. Keckler, Siva Kumar Sastry Hari, Siddharth Garg, Animashree Anandkumar, Timothy Tsai, Zahra Ghodsi, Iuri Frosio, Alejandro Troccoli
Extracting interesting scenarios from real-world data as well as generating failure cases is important for the development and testing of autonomous systems. We propose efficient mechanisms to both characterize and generate testing scenarios using a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::097671060e96d4d7e0e19dfb0c432a71
http://arxiv.org/abs/2103.07403
http://arxiv.org/abs/2103.07403
Autor:
Alex Nobbe, Siva Kumar Sastry Hari, Iuri Frosio, Jose Rodrigo Sanchez Vicarte, Christopher W. Fletcher, Abdulrahman Mahmoud, Sarita V. Adve, Neeraj Aggarwal
Publikováno v:
DSN Workshops
PyTorchFI is a runtime perturbation tool for deep neural networks (DNNs), implemented for the popular PyTorch deep learning platform. PyTorchFI enables users to perform perturbations on weights or neurons of DNNs at runtime. It is designed with the p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2b3c0b8dbe1c044fa68d9a405828c333
https://doi.org/10.1109/dsn-w50199.2020.00014
https://doi.org/10.1109/dsn-w50199.2020.00014
Publikováno v:
IEEE Transactions on Computational Imaging. 3:47-57
Neural networks are becoming central in several areas of computer vision and image processing and different architectures have been proposed to solve specific problems. The impact of the loss layer of neural networks, however, has not received much a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c1a8973991bf35b61bd55aa48de81995
https://doi.org/10.1109/tci.2016.2644865
https://doi.org/10.1109/tci.2016.2644865
Autor:
Iuri Frosio, Greg Heinrich
Publikováno v:
MLHPC@SC
Training intelligent agents through reinforcement learning is a notoriously unstable procedure. Massive parallelization on GPUs and distributed systems has been exploited to generate a large amount of training experiences and consequently reduce inst
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7c548a1e3969f4bcc8c17bf60ff12706
https://doi.org/10.1109/mlhpc49564.2019.00008
https://doi.org/10.1109/mlhpc49564.2019.00008
Publikováno v:
CVPR
Structural pruning of neural network parameters reduces computation, energy, and memory transfer costs during inference. We propose a novel method that estimates the contribution of a neuron (filter) to the final loss and iteratively removes those wi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4e1a133ece39f647e34a458ef6251dd9
https://doi.org/10.1109/cvpr.2019.01152
https://doi.org/10.1109/cvpr.2019.01152
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012458
ECCV (1)
ECCV (1)
Scene motion, multiple reflections, and sensor noise introduce artifacts in the depth reconstruction performed by time-of-flight cameras. We propose a two-stage, deep-learning approach to address all of these sources of artifacts simultaneously. We a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d59530dfae043e39051e35c45e2309b4
https://doi.org/10.1007/978-3-030-01246-5_23
https://doi.org/10.1007/978-3-030-01246-5_23
Publikováno v:
The Visual Computer. 32:663-674
We describe a method to compute the internal parameters (focal and principal point) of a camera with known position and orientation, based on the observation of two or more conics on a known plane. The conics can even be degenerate (e.g., pairs of li
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4624703dfa7049614011a115eb963b58
https://doi.org/10.1007/s00371-015-1089-8
https://doi.org/10.1007/s00371-015-1089-8