Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Tobias Jaeggli"'
Autor:
Patrick De Mazière, Joris Vangeneugden, Marc M. Van Hulle, Tobias Jaeggli, Luc Van Gool, Rufin Vogels
Publikováno v:
The Journal of Neuroscience. 31:385-401
Temporal cortical neurons are known to respond to visual dynamic-action displays. Many human psychophysical and functional imaging studies examining biological motion perception have used treadmill walking, in contrast to previous macaque single-cell
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e03d377490cd04c3dc3f45223278a8a6
https://doi.org/10.1523/jneurosci.2703-10.2011
https://doi.org/10.1523/jneurosci.2703-10.2011
Publikováno v:
Journal of Vision. 10:1-19
A vast literature exists on human biological motion perception in impoverished displays, e.g., point-light walkers. Less is known about the perception of impoverished biological motion displays in macaques. We trained 3 macaques in the discrimination
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3c8fd86cef9e0d7c5624c3f61c600cbf
https://doi.org/10.1167/10.4.22
https://doi.org/10.1167/10.4.22
Autor:
Cristi Prodan, Till Quack, Peter Cech, David Wisti, Franco Sebregondi, Tomas Carnecky, Philippe Messmer, Christian Wengert, Tobias Jaeggli
Publikováno v:
ACM Multimedia
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::25088dcaec60d6a92a05f311c859bdad
https://doi.org/10.1145/2072298.2072440
https://doi.org/10.1145/2072298.2072440
Publikováno v:
ICCV Workshops
We present an approach for unusual event detection, based on a tree of trackers. At lower levels, the trackers are trained on broad classes of targets. At higher levels, they aim at more specific targets. For instance, at the root, a general blob tra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::21f166f5a90eecf9f845f3c0bf8a0fdd
https://doi.org/10.1109/iccvw.2009.5457578
https://doi.org/10.1109/iccvw.2009.5457578
Publikováno v:
International Journal of Computer Vision, 83 (2)
International Journal of Computer Vision, 83 (2)
ISSN:0920-5691
ISSN:1573-1405
ISSN:0920-5691
ISSN:1573-1405
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::12a9dc524ebfc9101500a6c5d1730178
https://hdl.handle.net/20.500.11850/12384
https://hdl.handle.net/20.500.11850/12384
Publikováno v:
Human Motion – Understanding, Modeling, Capture and Animation ISBN: 9783540757023
Workshop on Human Motion
Workshop on Human Motion
We present a method to simultaneously estimate 3d body pose and action categories from monocular video sequences. Our approach learns a low-dimensional embedding of the pose manifolds using Locally Linear Embedding (LLE), as well as the statistical r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b4040f6d0366f9a8260aa902f73e1e9d
https://doi.org/10.1007/978-3-540-75703-0_4
https://doi.org/10.1007/978-3-540-75703-0_4
Publikováno v:
Computer Vision – ACCV 2007 ISBN: 9783540763857
ACCV (1)
ACCV (1)
We consider the problem of monocular 3d body pose tracking from video sequences. This task is inherently ambiguous. We propose to learn a generative model of the relationship of body pose and image appearance using a sparse kernel regressor. Within a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e3559115e531904f1b9c9c7a6331f455
https://doi.org/10.1007/978-3-540-76386-4_57
https://doi.org/10.1007/978-3-540-76386-4_57
Publikováno v:
Articulated Motion and Deformable Objects ISBN: 9783540360315
AMDO
AMDO
This paper considers the problem of monocular human body tracking using learned models. We propose to learn the joint probability distribution of appearance and body pose using a mixture of view-dependent models. In such a way the multimodal and nonl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5f24538d81944ac17601cf5450fabc52
https://doi.org/10.1007/11789239_51
https://doi.org/10.1007/11789239_51
Publikováno v:
CVPR Workshops
A system to acquire the 3D model of an object in a fast and easy way is presented. Models are produced by manipulating the object in front of the system. Both shape and texture are captured, integrated, and visualised online. This allows the user to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bb6c4ead561d29e92b524f31c0a9f7f5
https://doi.org/10.1109/cvpr.2004.295
https://doi.org/10.1109/cvpr.2004.295
Publikováno v:
SPIE Proceedings.
In this paper a new approach to 3D human body tracking is proposed. A sparse 3D reconstruction of the subject to be tracked is made using a structured light system consisting of a precalibrated LCD projector and a camera. At a number of points-of-int
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6bd905bbccb8fe1d44c58a63216a25a5
https://doi.org/10.1117/12.586684
https://doi.org/10.1117/12.586684