Zobrazeno 1 - 10
of 126
pro vyhledávání: '"Axel Pinz"'
Autor:
Martin Kronschläger, Hannes Siegl, Axel Pinz, Christoph Feichtenhofer, Wolf Buehl, Nino Hirnschall, Oliver Findl
Publikováno v:
BMC Ophthalmology, Vol 19, Iss 1, Pp 1-7 (2019)
Abstract Background The present study aims to investigate an automated qualitative and quantitative assessment system (Automated Quantification of After-Cataract [AQUA II]) of posterior capsule opacification (PCO) in high-resolution digital retroillu
Externí odkaz:
https://doaj.org/article/d11b71e05d01400d81441ac3c3f8f8cd
Autor:
Axel Pinz, Horst Bischof, Walter Kropatsch, Gerald Schweighofer, Yll Haxhimusa, Andreas Opelt, Adrian Ion
Publikováno v:
ELCVIA Electronic Letters on Computer Vision and Image Analysis, Vol 7, Iss 2 (2008)
The emerging discipline of cognitive vision requires a proper representation of visual information including spatial and temporal relationships, scenes, events, semantics and context. This review article summarizes existing representational schemes i
Externí odkaz:
https://doaj.org/article/13cafcf9f72d4bc29311cf11a564bb6e
Publikováno v:
International Journal of Computer Vision. 128:420-437
As the success of deep models has led to their deployment in all areas of computer vision, it is increasingly important to understand how these representations work and what they are capturing. In this paper, we shed light on deep spatiotemporal repr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cf3849f3ab10b6baee227daaec819d46
https://doi.org/10.1007/s11263-019-01225-w
https://doi.org/10.1007/s11263-019-01225-w
Autor:
Hannes Siegl, Nino Hirnschall, Axel Pinz, Oliver Findl, Wolf Buehl, Martin Kronschläger, Christoph Feichtenhofer
Publikováno v:
BMC Ophthalmology, Vol 19, Iss 1, Pp 1-7 (2019)
BMC Ophthalmology
BMC Ophthalmology
Background The present study aims to investigate an automated qualitative and quantitative assessment system (Automated Quantification of After-Cataract [AQUA II]) of posterior capsule opacification (PCO) in high-resolution digital retroillumination
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7c2a2908cc9a0116263497b69f2c5a93
http://link.springer.com/article/10.1186/s12886-019-1116-z
http://link.springer.com/article/10.1186/s12886-019-1116-z
Autor:
Axel Pinz, Filip Ilic
Publikováno v:
WACV
As top-down based approaches of object recognition from video are getting more powerful, a structured way to combine them with bottom-up grouping processes becomes feasible. When done right, the resulting representation is able to describe objects an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::072de253c943453f764bc29edfc9f32b
https://doi.org/10.1109/wacv45572.2020.9093410
https://doi.org/10.1109/wacv45572.2020.9093410
Autor:
Moritz Kampelmühler, Axel Pinz
Publikováno v:
WACV
Humans are able to precisely communicate diverse concepts by employing sketches, a highly reduced and abstract shape based representation of visual content. We propose, for the first time, a fully convolutional end-to-end architecture that is able to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5f4b3165b9fe7fb0d99c4daf7993970a
https://doi.org/10.1109/wacv45572.2020.9093440
https://doi.org/10.1109/wacv45572.2020.9093440
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 38:2389-2401
This paper presents Dynamically Pooled Complementary Features (DPCF), a unified approach to dynamic scene recognition that analyzes a short video clip in terms of its spatial, temporal and color properties. The complementarity of these properties is
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9a3827ad84323369b19012d1c597a6fc
https://doi.org/10.1109/tpami.2016.2526008
https://doi.org/10.1109/tpami.2016.2526008
Publikováno v:
CVPR
As the success of deep models has led to their deployment in all areas of computer vision, it is increasingly important to understand how these representations work and what they are capturing. In this paper, we shed light on deep spatiotemporal repr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cac995fdd6b78da5aaa137d95d92cb7d
https://doi.org/10.1109/cvpr.2018.00818
https://doi.org/10.1109/cvpr.2018.00818
Publikováno v:
Digital Applications in Archaeology and Cultural Heritage. 2:181-195
We present the micro- and mid-scale elements of an integrated multi-scalar solution to the 3D recording of rock-art sites in their landscape contexts. The photogrammetry-based solution integrates 3D models across vastly different scales: individual p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fbed216a9851811c0e1ff5b1c46d22b9
https://doi.org/10.1016/j.daach.2015.02.003
https://doi.org/10.1016/j.daach.2015.02.003
Publikováno v:
ICCV
Recent approaches for high accuracy detection and tracking of object categories in video consist of complex multistage solutions that become more cumbersome each year. In this paper we propose a ConvNet architecture that jointly performs detection an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1a3e1b5ce39014aefa7208a31fd25468
https://doi.org/10.1109/iccv.2017.330
https://doi.org/10.1109/iccv.2017.330