Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Jukka Peltomaki"'
Autor:
Atakan Dag, Farid Alijani, Jukka Peltomaki, Lauri Suomela, Esa Rahtu, Harry Edelman, Joni-Kristian Kämäräinen
Publikováno v:
Image Analysis ISBN: 9783031314377
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5bc6358a0c17600a94896b666e59ca9a
https://doi.org/10.1007/978-3-031-31438-4_22
https://doi.org/10.1007/978-3-031-31438-4_22
Autor:
Farid Alijani, Jukka Peltomaki, Jussi Puura, Heikki Huttunen, Joni-Kristian Kamarainen, Esa Rahtu
Publikováno v:
2022 26th International Conference on Pattern Recognition (ICPR).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::23a77177479d1b8d55d83478d0ecf648
https://doi.org/10.1109/icpr56361.2022.9956392
https://doi.org/10.1109/icpr56361.2022.9956392
Publikováno v:
ICPR
In this work, loop-closure detection from LiDAR scans is defined as an image re-identification problem. Re-identification is performed by computing Euclidean distances of a query scan to a gallery set of previous scans. The distances are computed in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4cb3a3fb779cc117283f3793c8f927ac
https://doi.org/10.1109/icpr48806.2021.9412843
https://doi.org/10.1109/icpr48806.2021.9412843
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030839055
SAFECOMP Workshops
SAFECOMP Workshops
Label noise is a primary point of interest for safety concerns in previous works as it affects the robustness of a machine learning system by a considerable amount. This paper studies the sensitivity of object detection loss functions to label noise
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3269cfa8813fce6b9842f1d54648f48f
https://trepo.tuni.fi/handle/10024/141904
https://trepo.tuni.fi/handle/10024/141904
Autor:
Jukka Peltomaki, Farid Alijani, Jussi Puura, Heikki Huttunen, Esa Rahtu, Joni-Kristian Kamarainen
We compare a state-of-the-art deep image retrieval and a deep place recognition method for place recognition using LiDAR data. Place recognition aims to detect previously visited locations and thus provides an important tool for navigation, mapping,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ac0311173555090297a5f4bc88ee8ea8
https://trepo.tuni.fi/handle/10024/143577
https://trepo.tuni.fi/handle/10024/143577
Publikováno v:
NORCAS
This paper studies the benefits of adding inexpensively gathered simulated data to improve the training of semantic segmentation models. We introduce our implementation to gather simulated datasets with minimal effort. In our implementation, we utili
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::54a8caeb77044981009a889aa1354977
https://doi.org/10.1109/norchip.2019.8906954
https://doi.org/10.1109/norchip.2019.8906954
Publikováno v:
EUVIP
This paper proposes an approach for rapid bounding box annotation for object detection datasets. The procedure consists of two stages: The first step is to annotate a part of the dataset manually, and the second step proposes annotations for the rema
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::02496b9395fa4cdb0eef02cf2a71a51e
http://arxiv.org/abs/1807.03142
http://arxiv.org/abs/1807.03142