Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Santos, Samuel P. dos"'
We investigate helicoidal surfaces in Euclidean space whose profile curves are frontals. Under certain conditions, these surfaces are framed base surfaces. We derive geometric invariants and curvatures for helicoidal surfaces, utilizing the curvature
Externí odkaz:
http://arxiv.org/abs/2412.10086
Publikováno v:
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV'25), 2025, pp. 1-11
Unsupervised domain adaptation (UDA) in videos is a challenging task that remains not well explored compared to image-based UDA techniques. Although vision transformers (ViT) achieve state-of-the-art performance in many computer vision tasks, their u
Externí odkaz:
http://arxiv.org/abs/2407.01375
Convolutional neural networks (CNNs) have achieved astonishing advances over the past decade, defining state-of-the-art in several computer vision tasks. CNNs are capable of learning robust representations of the data directly from the RGB pixels. Ho
Externí odkaz:
http://arxiv.org/abs/2309.11417
Autor:
Santos, Samuel Felipe dos, Berriel, Rodrigo, Oliveira-Santos, Thiago, Sebe, Nicu, Almeida, Jurandy
Deep learning has achieved state-of-the-art performance on several computer vision tasks and domains. Nevertheless, it still has a high computational cost and demands a significant amount of parameters. Such requirements hinder the use in resource-li
Externí odkaz:
http://arxiv.org/abs/2309.11464
Autor:
Santos, Samuel Felipe dos, Berriel, Rodrigo, Oliveira-Santos, Thiago, Sebe, Nicu, Almeida, Jurandy
Publikováno v:
22nd International Conference on Image Analysis and Processing (ICIAP'23), 2023, pp. 477-489
Deep learning has achieved state-of-the-art performance on several computer vision tasks and domains. Nevertheless, it still has a high computational cost and demands a significant amount of parameters. Such requirements hinder the use in resource-li
Externí odkaz:
http://arxiv.org/abs/2210.08101
We study singularities and geometric properties of surfaces given by the singular loci of normal congruence of frontals with pure-frontal singular points. These surfaces consist of the normal ruled surface and focal surfaces of the initial frontal. F
Externí odkaz:
http://arxiv.org/abs/2207.07009
Publikováno v:
Rev. Un. Mat. Argentina 67, no. 2 (2024), pp. 475-502
Near a singular point of a surface or a curve, geometric invariants diverge in general, and the orders of diverge, in particular the boundedness about these invariants represent geometry of the surface and the curve. In this paper, we study boundedne
Externí odkaz:
http://arxiv.org/abs/2206.11487
Publikováno v:
in 2021 25th Iberoamerican Congress on Pattern Recognition (CIARP), 2021, pp. 237-247
Most image data available are often stored in a compressed format, from which JPEG is the most widespread. To feed this data on a convolutional neural network (CNN), a preliminary decoding process is required to obtain RGB pixels, demanding a high co
Externí odkaz:
http://arxiv.org/abs/2104.00185
Autor:
Saji, Kentaro, Santos, Samuel P. dos
We study the geometry of bifurcation sets of generic unfoldings of $D_4^\pm$-functions. Taking blow-ups, we show each of the bifurcation sets of $D_4^\pm$-functions admit a parametrization as a surface in $R^3$. Using this parametrization, we investi
Externí odkaz:
http://arxiv.org/abs/2101.07967
Convolutional neural networks (CNNs) have achieved astonishing advances over the past decade, defining state-of-the-art in several computer vision tasks. CNNs are capable of learning robust representations of the data directly from the RGB pixels. Ho
Externí odkaz:
http://arxiv.org/abs/2012.14426