Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Radek Mackowiak"'
Light field applications, especially light field rendering and depth estimation, developed rapidly in recent years. While state-of-the-art light field rendering methods handle semi-transparent and reflective objects well, depth estimation methods eit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::95fc1139f315a122ce9176b142e36771
Publikováno v:
CVPR
With the maturing of deep learning systems, trustworthiness is becoming increasingly important for model assessment. We understand trustworthiness as the combination of explainability and robustness. Generative classifiers (GCs) are a promising class
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4e01fdbc5c2705b37a5926854fd886fb
http://arxiv.org/abs/2007.15036
http://arxiv.org/abs/2007.15036
Publikováno v:
3DV
We propose a method for depth estimation from light field data, based on a fully convolutional neural network architecture. Our goal is to design a pipeline which achieves highly accurate results for small- and wide-baseline light fields. Since light
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::24789e0f1b53d85ddbbfaa8f792c2a8b
Autor:
Niklas Beuter, Radek Mackowiak, Lucas Drumond, Ferran Diego, Omair Ghori, Björn Ommer, Miguel Ángel Bautista
Publikováno v:
Intelligent Vehicles Symposium
For an autonomous car, the ability to foresee a humans action is very useful for mitigating the risk of a possible collision. To humans this pedestrian intention foresight comes naturally as they are able to recognize another person's actions just by
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cb0ecc4dddc10da35739632b77544b9d
https://doi.org/10.1109/ivs.2018.8500657
https://doi.org/10.1109/ivs.2018.8500657
Publikováno v:
MultiMedia Modeling ISBN: 9783319276731
MMM (2)
MMM (2)
We present a novel approach to browse huge sets of video scenes using a hierarchical graph and visually sorted image maps allowing the user to explore the graph similar to navigation services. In a previous paper [1] we proposed a scheme to generate
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2a11325ed8a9419e63edd24bfae2524a
https://doi.org/10.1007/978-3-319-27674-8_43
https://doi.org/10.1007/978-3-319-27674-8_43
Publikováno v:
ISM
In this paper, we present a novel approach to reconstruct missing areas in facial images by using a series of Restricted Boltzman Machines (RBMs). RBMs created with a low number of hidden neurons generalize well and are able to reconstruct basic stru
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::10e3619bd6008cbaa99c912d6e83adc0
https://doi.org/10.1109/ism.2015.68
https://doi.org/10.1109/ism.2015.68
Publikováno v:
MultiMedia Modeling ISBN: 9783319144412
MMM (2)
MMM (2)
We present a graph-based browsing system for visually searching video clips in large collections. It is an extension of a previously proposed system ImageMap which allows visual browsing in millions of images using a hierarchical pyramid structure of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bd01756fec74d959387355a0b455ef20
https://doi.org/10.1007/978-3-319-14442-9_21
https://doi.org/10.1007/978-3-319-14442-9_21
Publikováno v:
MultiMedia Modeling ISBN: 9783319144412
MMM (2)
MMM (2)
In this paper we showcase ImageMap - an image browsing system to visually explore and search millions of images from stock photo agencies and the like. Similar to map services like Google Maps users may navigate through multiple image layers by zoomi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5ff3bad6a2daeb7c85e459bd07065910
https://doi.org/10.1007/978-3-319-14442-9_30
https://doi.org/10.1007/978-3-319-14442-9_30