Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Martin Köstinger"'
Publikováno v:
ICCV
In this paper, we raise important issues concerning the evaluation complexity of existing Mahalanobis metric learning methods. The complexity scales linearly with the size of the dataset. This is especially cumbersome on large scale or for real-time
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ae3709c4c75f60ab6274ce328d2b1e2d
https://doi.org/10.1109/iccv.2013.386
https://doi.org/10.1109/iccv.2013.386
Publikováno v:
CVPR
The development of complex, powerful classifiers and their constant improvement have contributed much to the progress in many fields of computer vision. However, the trend towards large scale datasets revived the interest in simpler classifiers to re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::378edc1d2a307f532457535dc5ac5c77
https://doi.org/10.1109/cvpr.2013.66
https://doi.org/10.1109/cvpr.2013.66
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783642406010
GCPR
TU Graz
GCPR
TU Graz
In this paper, we address the problem of efficient k-NN classification. In particular, in the context of Mahalanobis metric learning. Mahalanobis metric learning recently demonstrated competitive results for a variety of tasks. However, such approach
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::447e851cc7dc8cc5a3000979f5ff9b9c
https://doi.org/10.1007/978-3-642-40602-7_32
https://doi.org/10.1007/978-3-642-40602-7_32
Publikováno v:
ICIP
One central task in many visual surveillance scenarios is person re-identification, i.e., recognizing an individual person across a network of spatially disjoint cameras. Most successful recognition approaches are either based on direct modeling of t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e94b1a70e98463223cf9fe406ebfad0e
https://doi.org/10.1109/icip.2012.6467185
https://doi.org/10.1109/icip.2012.6467185
Publikováno v:
CVPR
In this paper, we raise important issues on scalability and the required degree of supervision of existing Mahalanobis metric learning methods. Often rather tedious optimization procedures are applied that become computationally intractable on a larg
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b4da5fbafba65a84583f6b5888813d3a
https://doi.org/10.1109/cvpr.2012.6247939
https://doi.org/10.1109/cvpr.2012.6247939
Publikováno v:
Computer Vision – ECCV 2012 ISBN: 9783642337826
ECCV (6)
ECCV (6)
Matching persons across non-overlapping cameras is a rather challenging task. Thus, successful methods often build on complex feature representations or sophisticated learners. A recent trend to tackle this problem is to use metric learning to find a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c6467dc14bbd40470263a24def4fe2bb
https://doi.org/10.1007/978-3-642-33783-3_56
https://doi.org/10.1007/978-3-642-33783-3_56
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783642327162
DAGM/OAGM Symposium
TU Graz
DAGM/OAGM Symposium
TU Graz
In this paper we address the problem that most face recognition approaches neglect that faces share strong visual similarities, which can be exploited when learning discriminative models. Hence, we propose to model face recognition as multi-task lear
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2905f705d6e79303aa1b490499dd22c4
https://doi.org/10.1007/978-3-642-32717-9_20
https://doi.org/10.1007/978-3-642-32717-9_20
Publikováno v:
BMVC
Object detection models based on the Implicit Shape Model (ISM) [3] use small, local parts that vote for object centers in images. Since these parts vote completely independently from each other, this often leads to false-positive detections due to r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a787f6882a44b4fbf8dae21b6a535168
https://doi.org/10.5244/c.26.40
https://doi.org/10.5244/c.26.40
Publikováno v:
ICCV Workshops
Face alignment is a crucial step in face recognition tasks. Especially, using landmark localization for geometric face normalization has shown to be very effective, clearly improving the recognition results. However, no adequate databases exist that
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a87dc7318c7c87989b911b8426a1c17a
https://doi.org/10.1109/iccvw.2011.6130513
https://doi.org/10.1109/iccvw.2011.6130513
Publikováno v:
AVSS
Videos are often associated with additional information that could be valuable for interpretation of their content. This especially applies for the recognition of faces within video streams, where often cues such as transcripts and subtitles are avai
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::890036d30943e60d445a1827c7f0cb67
https://doi.org/10.1109/avss.2011.6027287
https://doi.org/10.1109/avss.2011.6027287