Zobrazeno 1 - 10
of 63
pro vyhledávání: '"Ainouz, Samia"'
Autor:
Ruffino, Cyprien, Blin, Rachel, Ainouz, Samia, Gasso, Gilles, Hérault, Romain, Meriaudeau, Fabrice, Canu, Stéphane
Polarimetric imaging, along with deep learning, has shown improved performances on different tasks including scene analysis. However, its robustness may be questioned because of the small size of the training datasets. Though the issue could be solve
Externí odkaz:
http://arxiv.org/abs/2206.07431
The use of pseudo-labels prevails in order to tackle Unsupervised Domain Adaptive (UDA) Re-Identification (re-ID) with the best performance. Indeed, this family of approaches has given rise to several UDA re-ID specific frameworks, which are effectiv
Externí odkaz:
http://arxiv.org/abs/2112.12887
Unsupervised Domain Adaptation (UDA) for re-identification (re-ID) is a challenging task: to avoid a costly annotation of additional data, it aims at transferring knowledge from a domain with annotated data to a domain of interest with only unlabeled
Externí odkaz:
http://arxiv.org/abs/2110.07897
Person Re-Identification (re-ID) aims at retrieving images of the same person taken by different cameras. A challenge for re-ID is the performance preservation when a model is used on data of interest (target data) which belong to a different domain
Externí odkaz:
http://arxiv.org/abs/2009.09445
Publikováno v:
In Neurocomputing 28 November 2023 559
Object detection in road scenes is necessary to develop both autonomous vehicles and driving assistance systems. Even if deep neural networks for recognition task have shown great performances using conventional images, they fail to detect objects in
Externí odkaz:
http://arxiv.org/abs/1910.04870
Autor:
Ghani, Hasan Abdl, Laghmara, Hind, Ali, Sofiane Ahmed, Ainouz, Samia, Gao, Xing, Khemmar, Redouane
Publikováno v:
In IFAC PapersOnLine 2023 56(2):5685-5690
Publikováno v:
In Computer Vision and Image Understanding October 2022 223
Autor:
Ainouz, Samia
Ce travail concerne les développements nécessaires à la mise en oeuvre efficace de systèmes imageurs polarimétriques et comporte plusieurs volets allant de la théorie amont à l'utilisation d'algorithmes de traitement d'images spécifiques. Les
Externí odkaz:
http://tel.archives-ouvertes.fr/tel-00443685
http://tel.archives-ouvertes.fr/docs/00/44/36/85/PDF/Memoire_these.pdf
http://tel.archives-ouvertes.fr/docs/00/44/36/85/PDF/Memoire_these.pdf
Autor:
Anwer, Atif1,2 (AUTHOR) atif.anwer@insa-rouen.fr, Ainouz, Samia1 (AUTHOR), Saad, Mohamad Naufal Mohamad2 (AUTHOR), Ali, Syed Saad Azhar3 (AUTHOR), Meriaudeau, Fabrice4 (AUTHOR)
Publikováno v:
Sensors (14248220). Sep2022, Vol. 22 Issue 17, p6552. 20p.