Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Natalia, Neverova"'
Autor:
Yasutada Akiba, Angela M. Leung, Muhammad-Tariq Bashir, Ramin Ebrahimi, Jesse W. Currier, Natalia Neverova, Jonathan D. Kaunitz
Publikováno v:
Scientific Reports, Vol 12, Iss 1, Pp 1-10 (2022)
Abstract The lactoperoxidase (LPO)-hydrogen peroxide-halides reaction (LPO system) converts iodide and thiocyanate (SCN−) into hypoiodous acid (HOI) and hypothiocyanite (OSCN−), respectively. Since this system has been implicated in defense of th
Externí odkaz:
https://doaj.org/article/bfd80d54a6384e89885e881dfc096dc4
Autor:
Natalia Neverova, Christian Wolf, Griffin Lacey, Lex Fridman, Deepak Chandra, Brandon Barbello, Graham Taylor
Publikováno v:
IEEE Access, Vol 4, Pp 1810-1820 (2016)
We present a large-scale study exploring the capability of temporal deep neural networks to interpret natural human kinematics and introduce the first method for active biometric authentication with mobile inertial sensors. At Google, we have created
Externí odkaz:
https://doaj.org/article/03cb42ad0e0c4b2b94db67164bf0f8be
Autor:
Mohamed El Banani, Ignacio Rocco, David Novotny, Andrea Vedaldi, Natalia Neverova, Justin Johnson, Ben Graham
Video provides us with the spatio-temporal consistency needed for visual learning. Recent approaches have utilized this signal to learn correspondence estimation from close-by frame pairs. However, by only relying on close-by frame pairs, those appro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f4c75c3e7d3d125da275534697815e5e
http://arxiv.org/abs/2212.03236
http://arxiv.org/abs/2212.03236
Autor:
David Novotny, Ignacio Rocco, Samarth Sinha, Alexandre Carlier, Gael Kerchenbaum, Roman Shapovalov, Nikita Smetanin, Natalia Neverova, Benjamin Graham, Andrea Vedaldi
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Prior work for articulated 3D shape reconstruction often relies on specialized sensors (e.g., synchronized multi-camera systems), or pre-built 3D deformable models (e.g., SMAL or SMPL). Such methods are not able to scale to diverse sets of objects in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aa73bd8202af5deec71df39211813851
http://arxiv.org/abs/2112.12761
http://arxiv.org/abs/2112.12761
Autor:
Yasutada, Akiba, Angela M, Leung, Muhammad-Tariq, Bashir, Ramin, Ebrahimi, Jesse W, Currier, Natalia, Neverova, Jonathan D, Kaunitz
Publikováno v:
Scientific reports. 12(1)
The lactoperoxidase (LPO)-hydrogen peroxide-halides reaction (LPO system) converts iodide and thiocyanate (SCN
Publikováno v:
CVPR
We tackle the problem of learning the geometry of multiple categories of deformable objects jointly. Recent work has shown that it is possible to learn a unified dense pose predictor for several categories of related objects. However, training such m
Autor:
Natalia Neverova, Gael Kerchenbaum, David Novotny, Marvin Eisenberger, Andrea Vedaldi, Patrick Labatut, Daniel Cremers
Publikováno v:
CVPR
We present NeuroMorph, a new neural network architecture that takes as input two 3D shapes and produces in one go, i.e. in a single feed forward pass, a smooth interpolation and point-to-point correspondences between them. The interpolation, expresse
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::82975ccff9e0651673ec74f3c8b591b1
Publikováno v:
CVPR 2020
CVPR
CVPR
Recent contributions have demonstrated that it is possible to recognize the pose of humans densely and accurately given a large dataset of poses annotated in detail. In principle, the same approach could be extended to any animal class, but the effor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f031c3f9de1fabdfb920931692694a63
https://hdl.handle.net/21.11116/0000-0008-2E23-E21.11116/0000-0008-2E25-C
https://hdl.handle.net/21.11116/0000-0008-2E23-E21.11116/0000-0008-2E25-C
Autor:
Natalia Neverova, Christian Wolf, Elisa Fromont, Alain Trmeau, Rmi Emonet, Damien Muselet, Damien Fourure
Publikováno v:
Neurocomputing
Neurocomputing, Elsevier, 2017, 251, pp.68-80. ⟨10.1016/j.neucom.2017.04.014⟩
Neurocomputing, Elsevier, 2017, 251, pp.68-80. ⟨10.1016/j.neucom.2017.04.014⟩
International audience; We present an approach that leverages multiple datasets annotated for different tasks (e.g., classification with different labelsets) to improve the predictive accuracy on each individual dataset. Domain adaptation techniques