Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Till Kroeger"'
Autor:
Michael Gygli, Santiago Manen, Danda Pani Paudel, András Bódis-Szomorú, Carlos Eduardo Porto de Oliveira, Luc Van Gool, Till Kroeger, Dengxin Dai, Hayko Riemenschneider, Nikolay Kobyshev, Kenneth Vanhoey
Publikováno v:
SIGGRAPH Talks
VarCity - the Video is a short documentary-style CGI movie explaining the main outcomes of the 5-year Computer Vision research project VarCity. Besides a coarse overview of the research, we present the challenges that were faced in its production, in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1c3b151ec331b68e931f92f6148bd3a3
https://doi.org/10.1145/3084363.3085085
https://doi.org/10.1145/3084363.3085085
Publikováno v:
Computer Vision – ECCV 2016 ISBN: 9783319464923
ECCV (4)
ECCV (4)
Most recent works in optical flow extraction focus on the accuracy and neglect the time complexity. However, in real-life visual applications, such as tracking, activity detection and recognition, the time complexity is critical. We propose a solutio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f975de37eef7b7bf00a12c2cac4715fa
https://doi.org/10.1007/978-3-319-46493-0_29
https://doi.org/10.1007/978-3-319-46493-0_29
Publikováno v:
CVPR
© 2015 IEEE. Metric learning has proved very successful. However, human annotations are necessary. In this paper, we propose an unsupervised method, dubbed Metric Imitation (MI), where metrics over cheap features (target features, TFs) are learned b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0b5b08de620ea4ce910dfa112cca83a2
https://doi.org/10.1109/cvpr.2015.7298975
https://doi.org/10.1109/cvpr.2015.7298975
Publikováno v:
WACV Workshops
© 2015 IEEE. While vanishing point (VP) estimation has received extensive attention, most approaches focus on static images or perform detection and tracking separately. In this paper, we focus on man-made environments and propose a novel method for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::76828a924cfa4683e2c119fdd04a61ce
https://lirias.kuleuven.be/handle/123456789/532438
https://lirias.kuleuven.be/handle/123456789/532438
Publikováno v:
CVPR
© 2015 IEEE. We present a novel vanishing point (VP) detection and tracking algorithm for calibrated monocular image sequences. Previous VP detection and tracking methods usually assume known camera poses for all frames or detect and track separatel
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c9b35971d9e4e36b33abdcf54b84223a
https://lirias.kuleuven.be/handle/123456789/511427
https://lirias.kuleuven.be/handle/123456789/511427
Autor:
Till Kroeger, Luc Van Gool
Publikováno v:
Lecture Notes in Computer Science
Computer Vision – ECCV 2014 ISBN: 9783319106014
ECCV (5)
Computer Vision – ECCV 2014 ISBN: 9783319106014
ECCV (5)
Registering image data to Structure from Motion (SfM) point clouds is widely used to find precise camera location and orientation with respect to a world model. In case of videos one constraint has previously been unexploited: temporal smoothness. Wi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b24e19741a49dc4a59ce49739b526fdf
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319117515
We propose a new tracking-by-detection algorithm for multiple targets from multiple dynamic, unlocalized and unconstrained cameras. In the past tracking has either been done with multiple static cameras, or single and stereo dynamic cameras. We regis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f78f3ad9462a448be87a781efa903757
https://doi.org/10.1007/978-3-319-11752-2
https://doi.org/10.1007/978-3-319-11752-2