Zobrazeno 1 - 10 of 165 pro vyhledávání: '"Bernard Ghanem"'
1
Akademický článek
Hardware-accelerated integrated optoelectronic platform towards real-time high-resolution hyperspectral video understanding
Autor: Maksim Makarenko, Arturo Burguete-Lopez, Qizhou Wang, Silvio Giancola, Bernard Ghanem, Luca Passone, Andrea Fratalocchi
Publikováno v: Nature Communications, Vol 15, Iss 1, Pp 1-12 (2024)
Abstract Recent advancements in artificial intelligence have significantly expanded capabilities in processing language and images. However, the challenge of comprehensively understanding video content still needs to be solved. The main problem is th
Externí odkaz: https://doaj.org/article/e5fc9310aa5440579f657819add933c5
Zobrazit plný text záznamu
2
Akademický článek
Constrained Clustering: General Pairwise and Cardinality Constraints
Autor: Adel Bibi, Ali Alqahtani, Bernard Ghanem
Publikováno v: IEEE Access, Vol 11, Pp 5824-5836 (2023)
In this work, we study constrained clustering, where constraints are utilized to guide the clustering process. In existing works, two categories of constraints have been widely explored, namely pairwise and cardinality constraints. Pairwise constrain
Externí odkaz: https://doaj.org/article/97bf3ee149864caeb81906d8dbc4193f
Zobrazit plný text záznamu
3
Akademický článek
Scaling up SoccerNet with multi-view spatial localization and re-identification
Autor: Anthony Cioppa, Adrien Deliège, Silvio Giancola, Bernard Ghanem, Marc Van Droogenbroeck
Publikováno v: Scientific Data, Vol 9, Iss 1, Pp 1-9 (2022)
Measurement(s) Localization of soccer features Technology Type(s) Manual annotations
Externí odkaz: https://doaj.org/article/dbb6be7d12f445d79648d627f151b5fd
Zobrazit plný text záznamu
6
SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation
Autor: Bing Li, Cheng Zheng, Silvio Giancola, Bernard Ghanem
Publikováno v: Proceedings of the AAAI Conference on Artificial Intelligence. 36:1254-1262
We propose a novel scene flow estimation approach to capture and infer 3D motions from point clouds. Estimating 3D motions for point clouds is challenging, since a point cloud is unordered and its density is significantly non-uniform. Such unstructur
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d8081d4736e51e4a3b6ca19234b29df0
https://doi.org/10.1609/aaai.v36i2.20012
Zobrazit plný text záznamu
7
AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation
Autor: Chia-Wen Lin, Yitong Wang, Bernard Ghanem, Linlin Shen, Yuanlue Zhu, Bing Li
Publikováno v: IEEE Transactions on Multimedia. 24:4077-4091
In this paper, we propose a novel framework to translate a portrait photo-face into an anime appearance. Different from existing translation methods which do not designate specific styles, we aim to synthesize anime-faces which are style-consistent w
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7acd5397016f27b72ec450f291b5f592
https://doi.org/10.1109/tmm.2021.3113786
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje