Zobrazeno 1 - 10
of 56
pro vyhledávání: '"Jörgen Ahlberg"'
Publikováno v:
The Visual Computer. 39:219-237
Introduction of large training datasets was essential for the recent advancement and success of deep learning methods. Due to the difficulties related to biometric data collection, facial image datasets with biometric trait labels are scarce and usua
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9b2ead4c9f2dd7d3622845cf350396c0
https://doi.org/10.1007/s00371-021-02323-y
https://doi.org/10.1007/s00371-021-02323-y
Autor:
Jevgenijs Filipovs, Amanda Berg, Agris Brauns, Alekss Vecvanags, Dainis Jakovels, Jörgen Ahlberg
The surveillance of wild animal populations is important for wildlife sustainability, conservation and management. It has been estimated that the UAV-based survey of 100 ha large territory is ~10 times less time-consuming in comparison to surveys bas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::60ea9a1f086bf6d93ce0b5471fba0200
https://doi.org/10.5194/egusphere-egu21-14137
https://doi.org/10.5194/egusphere-egu21-14137
Face alignment is the process of determining a face shape given its location and size in an image. It is used as a basis for other facial analysis tasks and for human-machine interaction and augmented reality applications. It is a challenging problem
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9f8cdb89cc9e0933579900a736006e75
https://doi.org/10.1016/j.sigpro.2020.107755
https://doi.org/10.1016/j.sigpro.2020.107755
Facial expression recognition applications demand accurate and fast algorithms that can run in real time on platforms with limited computational resources. We propose an algorithm that bridges the gap between precise but slow methods and fast but les
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1f3f980c758b28b021b7e6e5f679a283
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-164181
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-164181
Publikováno v:
ICCV Workshops
Deep learning requires large amounts of annotated data. Manual annotation of objects in video is, regardless of annotation type, a tedious and time-consuming process. In particular, for scarcely used image modalities human annotationis hard to justif
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::de75a9ef13ca9cd7e1392401bd2a8808
https://doi.org/10.1109/iccvw.2019.00277
https://doi.org/10.1109/iccvw.2019.00277
Publikováno v:
VISIGRAPP (5: VISAPP)
Scopus-Elsevier
Scopus-Elsevier
Availability of large training datasets was essential for the recent advancement and success of deep learning methods. Due to the difficulties related to biometric data collection, datasets with age and gender annotations are scarce and usually limit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::34cb787342a582e6d05f31688649c228
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-154867
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-154867
Current best local descriptors are learned on a large dataset of matching and non-matching keypoint pairs. However, data of this kind is not always available since detailed keypoint correspondences can be hard to establish. On the other hand, we can
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::931dacee2b14181acc4b5b8c272e7c17
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-151931
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-151931
Publikováno v:
CVPR Workshops
Transformation of thermal infrared (TIR) images into visual, i.e. perceptually realistic color (RGB) images, is a challenging problem. TIR cameras have the ability to see in scenarios where vision is severely impaired, for example in total darkness o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::deb54c9cfed2e93e394b18ac06189097
https://doi.org/10.1109/cvprw.2018.00159
https://doi.org/10.1109/cvprw.2018.00159
We combine the near-sensor image processing concept with address-event representation leading to an intensity-ranking image sensor (IRIS) and show the benefits of using this type of sensor for image classification. The functionality of IRIS is to out
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b22bf2955d498726f30a31ba3ebc5296
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-151785
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-151785
Publikováno v:
Computer Graphics Forum. 34:251-261
An image mosaic is an assembly of a large number of small images, usually called tiles, taken from a specific dictionary/codebook. When viewed as a whole, the appearance of a single large image emerges, i.e. each tile approximates a small block of pi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aa5d1069e001cdef37a9f6a56bcf764b
https://doi.org/10.1111/cgf.12597
https://doi.org/10.1111/cgf.12597