Zobrazeno 1 - 10
of 201
pro vyhledávání: '"Patrick Bouthemy"'
Autor:
Antoine Basset, Patrick Bouthemy, Jérôme Boulanger, François Waharte, Jean Salamero, Charles Kervrann
Publikováno v:
BMC Bioinformatics, Vol 18, Iss 1, Pp 1-10 (2017)
Abstract Background Characterizing membrane dynamics is a key issue to understand cell exchanges with the extra-cellular medium. Total internal reflection fluorescence microscopy (TIRFM) is well suited to focus on the late steps of exocytosis at the
Externí odkaz:
https://doaj.org/article/7c49a51eccc44918bfb2bc9654c3005d
Publikováno v:
EURASIP Journal on Advances in Signal Processing, Vol 2009 (2009)
This paper is concerned with the estimation of the motions and the segmentation of the spatial supports of the different layers involved in transparent X-ray image sequences. Classical motion estimation methods fail on sequences involving transparent
Externí odkaz:
https://doaj.org/article/636d8de446134eb4b117f5ba72fa6a78
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45 (4), pp.4462-4473. ⟨10.1109/TPAMI.2022.3198480⟩
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45 (4), pp.4462-4473. ⟨10.1109/TPAMI.2022.3198480⟩
In this paper, we present a CNN-based fully unsupervised method for motion segmentation from optical flow. We assume that the input optical flow can be represented as a piecewise set of parametric motion models, typically, affine or quadratic motion
Autor:
Etienne Meunier, Patrick Bouthemy
Publikováno v:
BMVC 2021-32nd British Machine Vision Conference
BMVC 2021-32nd British Machine Vision Conference, Nov 2021, virtual conference, United Kingdom. pp.1-12
HAL
BMVC 2021-32nd British Machine Vision Conference, Nov 2021, virtual conference, United Kingdom. pp.1-12
HAL
International audience; We introduce a new paradigm for motion saliency (MS) which is an important issue in dynamic scene analysis. We formulate MS as a meta-task that can be instantiated for different tasks usually handled independently. To support
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::dca893f0604d4292d1ada3624a17ace0
https://hal.science/hal-03469574/file/BMVC2021_congres.pdf
https://hal.science/hal-03469574/file/BMVC2021_congres.pdf
Autor:
Juan-Manuel Perez-Rua, Patrick Bouthemy, Philip H. S. Torr, Tomas Crivelli, Patrick Pérez, Ondrej Miksik
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence, In press
IEEE Transactions on Pattern Analysis and Machine Intelligence, In press
Rotoscoping , the detailed delineation of scene elements through a video shot, is a painstaking task of tremendous importance in professional post-production pipelines. While pixel-wise segmentation techniques can help for this task, professional rot
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ca33fe8c6a36c74d6ee4007192f49386
https://ora.ox.ac.uk/objects/uuid:83c69946-d729-4b8a-b8ae-606454b136df
https://ora.ox.ac.uk/objects/uuid:83c69946-d729-4b8a-b8ae-606454b136df
Publikováno v:
ISBI 2020-IEEE 17th International Symposium on Biomedical Imaging
ISBI 2020-IEEE 17th International Symposium on Biomedical Imaging, Apr 2020, Iowa City, United States. pp.965-968, ⟨10.1109/ISBI45749.2020.9098690⟩
ISBI
ISBI 2020-IEEE 17th International Symposium on Biomedical Imaging, Apr 2020, Iowa City, United States. pp.965-968, ⟨10.1109/ISBI45749.2020.9098690⟩
ISBI
International audience; We present a 3D optical flow method for 3D fluorescence image sequences which preserves discontinuities in the computed flow field. We propose to minimize an energy function composed of a linearized 3D Census signature-based d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::add6c82a430c288a140f1d3ff4fc9733
https://hal.inria.fr/hal-03085956
https://hal.inria.fr/hal-03085956
Publikováno v:
Pattern Recognition Letters
Pattern Recognition Letters, 2019, 128, pp.298-305. ⟨10.1016/j.patrec.2019.09.016⟩
Pattern Recognition Letters, Elsevier, 2019, 128, pp.298-305. ⟨10.1016/j.patrec.2019.09.016⟩
Pattern Recognition Letters, 2019, 128, pp.298-305. ⟨10.1016/j.patrec.2019.09.016⟩
Pattern Recognition Letters, Elsevier, 2019, 128, pp.298-305. ⟨10.1016/j.patrec.2019.09.016⟩
International audience; The problem addressed in this paper appertains to the domain of motion saliency in videos. However this is a new problem since we aim to extract the temporal segments of the video where motion saliency is present. It turns out
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::15d58dfefae541b26bbfdddb38914432
https://inria.hal.science/hal-02345209
https://inria.hal.science/hal-02345209
Publikováno v:
International Journal of Computer Vision
International Journal of Computer Vision, 2017, pp.1-25. ⟨10.1007/s11263-017-1023-9⟩
International Journal of Computer Vision, 124(3)
International Journal of Computer Vision, 124(3), 287-311. Springer Netherlands
International Journal of Computer Vision, 2017, pp.1-25. ⟨10.1007/s11263-017-1023-9⟩
International Journal of Computer Vision, 124(3)
International Journal of Computer Vision, 124(3), 287-311. Springer Netherlands
This paper considers the problem of localizing actions in videos as a sequences of bounding boxes. The objective is to generate action proposals that are likely to include the action of interest, ideally achieving high recall with few proposals. Our
Publikováno v:
Journal of Mathematical Imaging and Vision
Journal of Mathematical Imaging and Vision, Springer Verlag, 2019, 61 (7), pp.1022-1036. ⟨10.1007/s10851-019-00883-2⟩
Journal of Mathematical Imaging and Vision, 2019, 61 (7), pp.1022-1036. ⟨10.1007/s10851-019-00883-2⟩
Journal of Mathematical Imaging and Vision, Springer Verlag, 2019, 61 (7), pp.1022-1036. ⟨10.1007/s10851-019-00883-2⟩
Journal of Mathematical Imaging and Vision, 2019, 61 (7), pp.1022-1036. ⟨10.1007/s10851-019-00883-2⟩
Parametric motion models are commonly used in image sequence analysis for different tasks. A robust estimation framework is usually required to reliably compute the motion model over the estimation support in the presence of outliers, while the choic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dc00671348b8d3d13ca56a48eb2eb7e3
https://hal.archives-ouvertes.fr/hal-02315977
https://hal.archives-ouvertes.fr/hal-02315977
Publikováno v:
ICIP 2019-IEEE International Conference on Image Processing
ICIP 2019-IEEE International Conference on Image Processing, Sep 2019, Taipei, Taiwan. pp.4469-4473, ⟨10.1109/ICIP.2019.8803542⟩
ICIP 2019-IEEE International Conference on Image Processing, Sep 2019, Taipei, Taiwan. pp.4469-4473, ⟨10.1109/ICIP.2019.8803542⟩
The paper addresses the problem of motion saliency in videos, that is, identifying regions that undergo motion departing from its context. We propose a new unsupervised paradigm to compute motion saliency maps. The key ingredient is the flow inpainti