Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Georg Waltner"'
Publikováno v:
Image Analysis and Processing – ICIAP 2022 ISBN: 9783031064265
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::415b38cee74bc38203af06690ff6f00c
https://doi.org/10.1007/978-3-031-06427-2_4
https://doi.org/10.1007/978-3-031-06427-2_4
Publikováno v:
WACV
We introduce a simple yet effective fusion method of LiDAR and RGB data to segment LiDAR point clouds. Utilizing the dense native range representation of a LiDAR sensor and the setup calibration, we establish point correspondences between the two inp
Publikováno v:
ITSC
Adapting detectors to new datasets is needed in scenarios where a user has a specific dataset that contains novel classes or is recorded in a setting where a pretrained detector fails. While detectors based on Convolutional Neural Networks (CNNs) are
Autor:
Thomas Holzmann, Patrick Ruprecht, Michael Maurer, Michael Opitz, Georg Waltner, Friedrich Fraundorfer, Horst Bischof, Horst Possegger
Publikováno v:
ITSC
Automated toll systems rely on proper classification of the passing vehicles. This is especially difficult when the images used for classification only cover parts of the vehicle. To obtain information about the whole vehicle. we reconstruct the vehi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6882eb376be16354b6c090e02462d8c4
http://arxiv.org/abs/1805.03511
http://arxiv.org/abs/1805.03511
Publikováno v:
TU Graz
Learning similarity functions between image pairs with deep neural networks yields highly correlated activations of embeddings. In this work, we show how to improve the robustness of such embeddings by exploiting the independence within ensembles. To
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::76f5161a1f9db646301afadf3238c1e0
http://arxiv.org/abs/1801.04815
http://arxiv.org/abs/1801.04815
Publikováno v:
ICCV
TU Graz
TU Graz
Learning similarity functions between image pairs with deep neural networks yields highly correlated activations of large embeddings. In this work, we show how to improve the robustness of embeddings by exploiting independence in ensembles. We divide
Autor:
Michael Schwarz, Anna Maria Weber, Georg Waltner, Lucas Paletta, Irene Schmid, Meinrad Lindschinger, Patrick Luley, Walter Scheitz, Horst Bischof, Stefan Ladstätter
Publikováno v:
New Trends in Image Analysis and Processing – ICIAP 2017 ISBN: 9783319707419
ICIAP Workshops
ICIAP Workshops
Daily appropriate decision making on nutrition requires application of knowledge where it matters, and being adjusted to the individual requirements. We present a highly personalized mobile application that assists the user in appropriate food choice
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9c6af67c92b758c873c40a5e3a1ecb44
https://doi.org/10.1007/978-3-319-70742-6_36
https://doi.org/10.1007/978-3-319-70742-6_36
Publikováno v:
CVPR
We present a novel video saliency detection method to support human activity recognition and weakly supervised training of activity detection algorithms. Recent research has emphasized the need for analyzing salient information in videos to minimize
Autor:
Michael Schwarz, Anna Maria Weber, Horst Bischof, Stefan Ladstätter, Lucas Paletta, Georg Waltner, Irene Schmid, Patrick Luley, Meinrad Lindschinger
Publikováno v:
New Trends in Image Analysis and Processing--ICIAP 2015 Workshops ISBN: 9783319232218
ICIAP Workshops
ICIAP Workshops
The prevention of cardiovascular diseases becomes more and more important, as malnutrition accompanies today’s fast moving society. While most people know the importance of adequate nutrition, information on advantageous food is often not at hand,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b0781b65a99cdc8e41d36d11f0c27350
https://doi.org/10.1007/978-3-319-23222-5_52
https://doi.org/10.1007/978-3-319-23222-5_52
Publikováno v:
TU Graz
Activity recognition in sport is an attractive field for computer vision research. Game, player and team analysis are of great interest and research topics within this field emerge with the goal of automated analysis. The very specific underlying rul
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f6fcc636d7bf81a1f6eec07b38f823f0