Artículos

Artículos Encontrados 128 registros  anterior11 - 20siguientefinal  ir al registro: La búsqueda tardó 0.01 segundos. 
11.
16 p, 5.6 MB Co-Training for On-Board Deep Object Detection / Villalonga, Gabriel (Centre de Visió per Computador (Bellaterra, Catalunya)) ; López Peña, Antonio M. (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)
Providing ground truth supervision to train visual models has been a bottleneck over the years, exacerbated by domain shifts which degenerate the performance of such models. This was the case when visual tasks relied on handcrafted features and shallow machine learning and, despite its unprecedented performance gains, the problem remains open within the deep learning paradigm due to its data-hungry nature. [...]
2020 - 10.1109/ACCESS.2020.3032024
IEEE Access, Vol. 8 (October 2020) p. 194441-194456  
12.
14 p, 840.3 KB Expressive Color Visual Secret Sharing with Color to Gray & Back and Cosine Transform / Chaturvedi, Ratnesh Naresh (Symbiosis International University. Symbiosis Institute of Technology) ; Thepade, Sudeep D. (Savitribai Phule Pune University. Department of Computer Engineering) ; Ahirrao, Swati (Symbiosis International University. Symbiosis Institute of Technology) ; Kothari, Sonali (Symbiosis International University. Symbiosis Institute of Technology)
Color Visual Secret Sharing (VSS) is an essential form of VSS. It is so because nowadays, most people like to share visual data as a color image. There are color VSS schemes capable of dealing with halftone color images or color images with selected colors, and some dealing with natural color images, which generate low quality of recovered secret. [...]
2023 - 10.5565/rev/elcvia.1405
ELCVIA : Electronic Letters on Computer Vision and Image Analysis, Vol. 22 Núm. 1 (2023) , 1-14 (Regular Issue)  
13.
12 p, 3.9 MB Weather Classification by Utilizing Synthetic Data / Minhas, Saad (University of Essex. School of Computer Science and Electrical Engineering) ; Khanam, Zeba (University of Essex. School of Computer Science and Electrical Engineering) ; Ehsan, Shoaib (University of Essex. School of Computer Science and Electrical Engineering) ; McDonald-Maier, Klaus (University of Essex. School of Computer Science and Electrical Engineering) ; Hernandez-Sabaté, Aura (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)
Weather prediction from real-world images can be termed a complex task when targeting classification using neural networks. Moreover, the number of images throughout the available datasets can contain a huge amount of variance when comparing locations with the weather those images are representing. [...]
2022 - 10.3390/s22093193
Sensors (Basel, Switzerland), Vol. 22, Issue 9 (April 2022) , art. 3193  
14.
37 p, 1.8 MB The Barcelona historical marriage database and the Baix Llobregat demographic database : from algorithms for handwriting recognition to individual-level demographic and socioeconomic data / Pujadas-Mora, Joana Maria 1977- (Centre d'Estudis Demogràfics) ; Fornés, Alícia (Centre de Visió per Computador (Bellaterra, Catalunya)) ; Ramos Terrades, Oriol (Centre de Visió per Computador (Bellaterra, Catalunya)) ; Lladós, Josep (Centre de Visió per Computador (Bellaterra, Catalunya)) ; Chen, Jialuo (Centre de Visió per Computador (Bellaterra, Catalunya)) ; Valls Fígols, Miquel (Centre d'Estudis Demogràfics) ; Cabré, Anna, 1943- (Centre d'Estudis Demogràfics)
The Barcelona Historical Marriage Database (BHMD) gathers records of the more than 600,000 marriages celebrated in the Diocese of Barcelona and their taxation registered in Barcelona Cathedral's so-called Marriage Licenses Books for the long period 1451-1905 and the BALL Demographic Database brings together the individual information recorded in the population registers, censuses and fiscal censuses of the main municipalities of the county of Baix Llobregat (Barcelona). [...]
2022 - 10.51964/hlcs11971
Historical life course studies, Vol. 12 Núm. 5 (2022) , p. 99-132  
15.
4 p, 168.5 KB Editors' note : L1 teaching in the Czech Republic, tendencies and challenges / Hurytová, Ivana (Charles University in Prague)
This special issue presents the situation in L1 teaching in the Czech Republic, some of its tendencies and challenges. One invited senior researcher, two doctoral students and a fresh postdoctoral researcher from four universities across the Czech Republic present their interests and conclusions in three articles and one interview.
Aquest número especial presenta la situació de l'ensenyament de L1 a la República Txeca, tendències i reptes. Un investigador sènior convidat, dos estudiants de doctorat i un nou investigador postdoctoral de quatre universitats de la República Txeca presenten els seus interessos i conclusions en tres articles i una entrevista.
Este número especial presenta la situación de la enseñanza de L1 en la República Checa, tendencias y desafíos. Un investigador principal invitado, dos estudiantes de doctorado y un nuevo investigador posdoctoral de cuatro universidades de la República Checa presentan sus intereses y conclusiones en tres artículos y una entrevista.
Ce numéro spécial présente la situation de l'enseignement de la L1 en République tchèque, quelques-unes de ses tendances et défis. Un chercheur senior invité, deux doctorants et un nouveau chercheur postdoctoral de quatre universités de la République tchèque présentent leurs intérêts et leurs conclusions dans trois articles et une interview.

2022 - 10.5565/rev/jtl3.1202
Bellaterra journal of teaching and learning language and literature, Vol. 15 Núm. 4 (2022) , p. e1202 (Editors' Note)  
16.
18 p, 597.1 KB Todos marcharon hacia el bosque : el virtuoso ejercicio de gestionar la naturaleza en la Edad Moderna / Versteegen, Gijs (Universidad Rey Juan Carlos) ; Guillén Berrendero, José Antonio (Universidad Rey Juan Carlos)
El texto que presentamos ofrece un análisis de la relación del hombre con la naturaleza durante la Edad Moderna. Para ello partimos de considerar que la naturaleza presenta una doble dimensión: es espacio de aprovisionamiento y escenario de reflexión. [...]
El text que presentem ofereix una anàlisi de la relació de l'home amb la natura durant l'Edat Moderna. Per a això partim de considerar que la natura presenta una doble dimensió: l'espai d'avituallament i l'escenari de reflexió. [...]
This text offers an analysis of the relationship between man and nature during the Early Modern Age. We first considering the double dimension of nature as a provisioning space and as a scenario of reflection. [...]

2020 - 10.5565/rev/manuscrits.294
Manuscrits : revista d'història moderna, Vol. 42 (2020) , p. 245-262 (Dosier)  
17.
22 p, 1.3 MB Robust pedestrian detection and path prediction using mmproved YOLOv5 / Hajari, Kamal Omprakash (Yeshwantrao Chavan College of Engineering) ; Gawande, Ujwalla (Yeshwantrao Chavan College of Engineering) ; Golhar, Yogesh (St. Vincent Palloti College of Engineering and Technology)
In vision-based surveillance systems, pedestrian recognition and path prediction are critical concerns. Advanced computer vision applications, on the other hand, confront numerous challenges due to differences in pedestrian postures and scales, backdrops, and occlusion. [...]
2022 - 10.5565/rev/elcvia.1538
ELCVIA : Electronic Letters on Computer Vision and Image Analysis, Vol. 21 Núm. 2 (2022) , p. 40-61 (Regular Issue)  
18.
6 p, 191.1 KB La sexualidad del rostro : revelación artificial y desprogramación material / Voto, Cristina
El artículo propone, desde una perspectiva de género, un análisis semiótico de la performatividad de la visión artificial en el ámbito de la producción de imágenes en la era digital. A partir de una puesta en diálogo entre la investigación basada en la inteligencia artificial Deep Neural Networks are More Accurate Than Humans at Detecting Sexual Orientation From Facial Images, de Michal Kosinski y Yilun Wang, de la Universidad de Stanford y la exhibición "Sexo, imagen y algoritmos: homosexual data", del artista chileno Felipe Rivas San Martín, se busca reflexionar sobre el actual proceso de algoritmización de la identidad sexual y genérica y opacar las retóricas transparentes y reveladoras de la inteligencia artificial por medio de la práctica artística.
The paper proposes, from a gender perspective, a semiotic analysis of the performativity of computer vision in the Digital Age. Starting from a dialogue between the research in Artificial Intelligence Deep neural networks are more accurate than humans at detecting sexual orientation from facial images, by Michal Kosinski and Yilun Wang from Stanford University and the exhibition Sex, image and algorithms: homosexual data, by Chilean artist Felipe Rivas San Martín, it seeks to reflect on the current process of algorithmization of sexuality and gender identity and to mattify the transparent and revealing rhetoric of artificial intelligence through artistic practice.

2022 - 10.35659/designis.i36p129-138
DeSignis, Núm. 36 (2022) , p. 129-138 (Escenarios/Scenery)  
19.
10 p, 2.2 MB Feature selection based on discriminative power under uncertainty for computer vision applications / Chakroun, Marwa (University of Sfax. Control and Energy Management Lab) ; Bouhamed, Sonda Ammar (University of Sfax. Control and Energy Management Lab) ; Kallel, Imene Khanfir (University of Sfax. Control and Energy Management Lab) ; Solaiman, Basel (IMT Atlantique (Brest, França)) ; Derbel, Houda (University of Sfax. Control and Energy Management Lab)
Feature selection is a prolific research field, which has been widely studied in the last decades and has been successfully applied to numerous computer vision systems. It mainly aims to reduce the dimensionality and thus the system complexity. [...]
2022 - 10.5565/rev/elcvia.1361
ELCVIA : Electronic Letters on Computer Vision and Image Analysis, Vol. 21 Núm. 1 (2022) , p. 111-120 (Regular Issue)  
20.
22 p, 2.1 MB Hierarchical novelty detection for traffic sign recognition / Ruiz López, Idoia (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació) ; Serrat Gual, Joan (Centre de Visió per Computador (Bellaterra, Catalunya))
Recent works have made significant progress in novelty detection, i. e. , the problem of detecting samples of novel classes, never seen during training, while classifying those that belong to known classes. [...]
2022 - 10.3390/s22124389
Sensors (Basel, Switzerland), Vol. 22, Issue 12 (June 2022) , art. 4389  

Artículos : Encontrados 128 registros   anterior11 - 20siguientefinal  ir al registro:
¿Le interesa recibir alertas sobre nuevos resultados de esta búsqueda?
Defina una alerta personal vía correo electrónico o subscríbase al canal RSS.