Zobrazeno 1 - 10
of 11 395
pro vyhledávání: '"A Kacem"'
Autor:
Rathinam, Arunkumar, Pauly, Leo, Shabayek, Abd El Rahman, Rharbaoui, Wassim, Kacem, Anis, Gaudillière, Vincent, Aouada, Djamila
Multispectral pedestrian detection has gained significant attention in recent years, particularly in autonomous driving applications. To address the challenges posed by adversarial illumination conditions, the combination of thermal and visible image
Externí odkaz:
http://arxiv.org/abs/2411.03576
Autor:
Karadeniz, Ahmet Serdar, Mallis, Dimitrios, Mejri, Nesryne, Cherenkova, Kseniya, Kacem, Anis, Aouada, Djamila
This work presents DAVINCI, a unified architecture for single-stage Computer-Aided Design (CAD) sketch parameterization and constraint inference directly from raster sketch images. By jointly learning both outputs, DAVINCI minimizes error accumulatio
Externí odkaz:
http://arxiv.org/abs/2410.22857
Autor:
Sosa, Jose, Aloulou, Mohamed, Rukhovich, Danila, Sleimi, Rim, Changaival, Boonyarit, Kacem, Anis, Aouada, Djamila
Self-supervised pre-training has proven highly effective for many computer vision tasks, particularly when labelled data are scarce. In the context of Earth Observation (EO), foundation models and various other Vision Transformer (ViT)-based approach
Externí odkaz:
http://arxiv.org/abs/2409.18536
We consider an infinite-dimension SIS model introduced by Delmas, Dronnier and Zitt, with a more general incidence rate, and study its equilibria. Unsurprisingly, there exists at least one endemic equilibrium if and only if the basic reproduction num
Externí odkaz:
http://arxiv.org/abs/2408.00034
Autor:
Karadeniz, Ahmet Serdar, Mallis, Dimitrios, Mejri, Nesryne, Cherenkova, Kseniya, Kacem, Anis, Aouada, Djamila
We propose PICASSO, a novel framework CAD sketch parameterization from hand-drawn or precise sketch images via rendering self-supervision. Given a drawing of a CAD sketch, the proposed framework turns it into parametric primitives that can be importe
Externí odkaz:
http://arxiv.org/abs/2407.13394
Autor:
Dupont, Elona, Cherenkova, Kseniya, Mallis, Dimitrios, Gusev, Gleb, Kacem, Anis, Aouada, Djamila
3D reverse engineering, in which a CAD model is inferred given a 3D scan of a physical object, is a research direction that offers many promising practical applications. This paper proposes TransCAD, an end-to-end transformer-based architecture that
Externí odkaz:
http://arxiv.org/abs/2407.12702
Autor:
Ben Hamida, Amal1,2 (AUTHOR) amal.ben-hamida@etu.univ-lyon1.fr, Kacem, Manel2 (AUTHOR), de Peretti, Christian1,3 (AUTHOR), Belkacem, Lotfi2 (AUTHOR)
Publikováno v:
International Journal of Market Research. Nov2024, Vol. 66 Issue 6, p810-831. 22p.
Hardware-aware Neural Architecture Search approaches (HW-NAS) automate the design of deep learning architectures, tailored specifically to a given target hardware platform. Yet, these techniques demand substantial computational resources, primarily d
Externí odkaz:
http://arxiv.org/abs/2404.12403
In this paper, the vibration energy localization in coupled nonlinear oscillators is investigated, based on the creation of standing solitons. The main objective is to establish a design methodology for mechanical lattices using the Nonlinear Schr\"o
Externí odkaz:
http://arxiv.org/abs/2403.05176
Autor:
Khan, Mohammad Sadil, Dupont, Elona, Ali, Sk Aziz, Cherenkova, Kseniya, Kacem, Anis, Aouada, Djamila
Reverse engineering in the realm of Computer-Aided Design (CAD) has been a longstanding aspiration, though not yet entirely realized. Its primary aim is to uncover the CAD process behind a physical object given its 3D scan. We propose CAD-SIGNet, an
Externí odkaz:
http://arxiv.org/abs/2402.17678