Resultats globals: 12 registres trobats en 0.02 segons.
Articles, 9 registres trobats
Documents de recerca, 3 registres trobats
Articles 9 registres trobats  
1.
10 p, 659.4 KB A Flexible Outlier Detector Based on a Topology Given by Graph Communities / Ramos Terrades, Oriol (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació) ; Berenguel Centeno, Albert (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació) ; Gil, Debora (Centre de Visió per Computador (Bellaterra, Catalunya))
Outlier detection is essential for optimal performance of machine learning methods and statistical predictive models. Their detection is especially determinant in small sample size unbalanced problems, since in such settings outliers become highly influential and significantly bias models. [...]
2022 - 10.1016/j.bdr.2022.100332
Big Data Research, Vol. 29 (August 2022) , art. 100332  
2.
4 p, 107.2 KB Learning audio and image representations with bio-inspired trainable feature extractors / Strisciuglio, Nicola (University of Groningen. Johann Bernoulli Institute for Mathematics and Computer Science)
Since when very young, we can quickly learn new concepts, and distinguish between different kinds of object or sound. If we see a single object or hear a particular sound, we are then able to recognize such sample or even different versions of it in other scenarios. [...]
2017 - 10.5565/rev/elcvia.1128
ELCVIA : Electronic Letters on Computer Vision and Image Analysis, Vol. 16 Núm. 2 (2017) , p. 17-20 (Special Issue on Recent PhD Thesis Dissemination (2017))  
3.
16 p, 2.3 MB Semantic Video Concept Detection using Novel Mixed-Hybrid-Fusion Approach for Multi-Label Data / Janwe, Nitin Jagannathrao ; Bhoyar, Kishor (Yeshwantrao Chavan College of Engineering (Nagpur, Índia))
The performance of the semantic concept detection method depends on, the selection of the low-level visual features used to represent key-frames of a shot and the selection of the feature-fusion method used. [...]
2017 - 10.5565/rev/elcvia.927
ELCVIA : Electronic Letters on Computer Vision and Image Analysis, Vol. 16 Núm. 3 (2017) , p. 14-29 (Regular Issue)  
4.
18 p, 1.2 MB Robust Real-Time Gradient-based Eye Detection and Tracking Using Transform Domain and PSO-Based Feature Selection / Salehi, Nasrin (Isfahan University (Iran). Department of Artificial Intelligence) ; Keyvanara, Maryam (Isfahan University (Iran). Department of Artificial Intelligence) ; Monadjemi, Amirhassan (Isfahan University (Iran). Department of Artificial Intelligence)
Despite numerous research on eye detection and tracking, this field of study remains challenging due to the individuality of eyes, occlusion, and variability in scale, location, and light conditions. [...]
2017 - 10.5565/rev/elcvia.811
ELCVIA : Electronic Letters on Computer Vision and Image Analysis, Vol. 16 Núm. 1 (2017) , p. 15-32 (Regular Issue)  
5.
10 p, 3.3 MB Detection and Classification of Multiple Objects using an RGB-D Sensor and Linear Spatial Pyramid Matching / Dimitriou, Michalis (Technological Educational Institute of Crete. Applied Informatics and Multimedia Department) ; Kounalakis, Tsampikos (Brunel University. Departament of Electronic and Computer Engineering) ; Vidakis, Nikolaos (Technological Educational Institute of Crete. Applied Informatics and Multimedia Department) ; Triantafyllidis, Georgios (Aalborg University Copenhagen. Medialogy Section)
This paper presents a complete system for multiple object detection and classification in a 3D scene using an RGB-D sensor such as the Microsoft Kinect sensor. Successful multiple object detection and classification are crucial features in many 3D computer vision applications. [...]
2013 - 10.5565/rev/elcvia.523
ELCVIA : Electronic Letters on Computer Vision and Image Analysis, Vol. 12, Núm. 2 (2013) , p. 78-87  
6.
15 p, 174.7 KB A Robust Multi-Feature Cut Detection Algorithm for Video Segmentation / Ciocca, Gianluigi (Università degli Studi di Milano-Bicocca. Department of Informatics, Systems and Communication)
Video segmentation is the first task in almost all video analysis applications. It consists in identifying the boundaries of the meaningful video units (shots). Without a doubt, cuts are the most common among production effects that characterize the shot boundaries. [...]
2010 - 10.5565/rev/elcvia.335
ELCVIA : Electronic Letters on Computer Vision and Image Analysis, Vol. 9, Núm. 1 ( 2010) , p. 32-46  
7.
18 p, 1016.5 KB Enhancing Sensor Measurements through Wide Baseline Stereo Images / Elias, Rimon (German University in Cairo (El Caire, Egipte). Department of Computer Science and Engineering)
In this paper, we suggest an algorithm to enhance the accuracy of sensor measurements representing camera parameters. The process proposed is based solely on a pair of wide baseline (or sparse view) images. [...]
2008 - 10.5565/rev/elcvia.222
ELCVIA : Electronic Letters on Computer Vision and Image Analysis, V. 7 n. 3 (2008) p. 36-53  
8.
12 p, 1.1 MB Automatic Detection of Facial Midline And Its Contributions To Facial Feature Extraction / Nakao, Nozomi (Mie University (Japó). Graduate School of Engineering) ; Ohyama, Wataru (Mie University (Japó). Graduate School of Engineering) ; Wakabayashi, Tetsushi (Mie University (Japó). Graduate School of Engineering) ; Kimura, Fumitaka (Mie University (Japó). Graduate School of Engineering)
We propose a novel approach for detection of the facial midline from a frontal face image. Using midline as a guide reduces computational cost required for facial feature extraction (FFE) because the midline is capable of restricting multi-dimensional searching process into one-dimensional search. [...]
2007 - 10.5565/rev/elcvia.142
ELCVIA : Electronic Letters on Computer Vision and Image Analysis, V. 6 n. 3 (2007) p. 55-65  
9.
14 p, 590.0 KB A robust feature tracker for active surveillance of outdoor scenes / Foresti, G. L. (University of Udine (Itàlia). Departement of Mathematics and Computer Science) ; Micheloni, C. (University of Udine (Itàlia). Departement of Mathematics and Computer Science)
In this paper, we propose a robust real-time object detection system for outdoor image sequences acquired by an active camera. The system is able to compensate background changes due to the camera motion and to detect mobile objects in the scene. [...]
2002 - 10.5565/rev/elcvia.60
ELCVIA : Electronic Letters on Computer Vision and Image Analysis, V. 1 n. 1 (2002) p. 21-34  

Documents de recerca 3 registres trobats  
1.
10 p, 449.4 KB Anàlisi del percentatge de tweets negatius en perfils de Twitter / Serra Fernández, Mateu ; Espinosa, Antonio, dir. (Universitat Autònoma de Barcelona. Departament d'Arquitectura de Computadors i Sistemes Operatius) ; Universitat Autònoma de Barcelona. Escola d'Enginyeria
Les xarxes socials s'han convertit en una forma molt popular de comunicació i interacció social en línia, i cada dia milions d'usuaris publiquen i comparteixen contingut en Twitter. No obstant això, l'aparició de comentaris negatius o ofensius en les publicacions s'ha convertit en un problema comú en les xarxes socials, la qual cosa pot generar un ambient tòxic i afectar negativament l'experiència dels usuaris.
Las redes sociales se han convertido en una forma muy popular de comunicación e interacción social en línea, y cada día millones de usuarios publican y comparten contenido en Twitter. Sin embargo, la aparición de comentarios negativos u ofensivos en las publicaciones se ha convertido en un problema común en las redes sociales, lo cual puede generar un ambiente tóxico y afectar negativamente la experiencia de los usuarios.
Social media has become a very popular form of online communication and social interaction, and every day millions of users post and share content on Twitter. However, the appearance of negative or offensive comments on posts has become a common problem on social networks, which can create a toxic environment and negatively affect the user experience.

2023
Enginyeria de Dades [1394]  
2.
10 p, 1.6 MB Software para la detección y el reconocimiento de rostros / Cazorla Martínez, Rafael ; Serra Sagristà, Joan, dir. (Universitat Autònoma de Barcelona. Departament d'Enginyeria de la Informació i de les Comunicacions) ; Universitat Autònoma de Barcelona. Escola d'Enginyeria
En los últimos años, las técnicas de detección y de reconocimiento facial han evolucionado mucho. Dado que este tipo de técnicas tienen muchas aplicaciones útiles en campos muy diversos como la biometría, la clasificación de imágenes o la seguridad, se han destinado muchos esfuerzos tanto económicos como científicos para tratar de mejorarlas. [...]
In recent years, face detection and face recognition techniques have been improved. All these techniques have many useful applications and can be applied in many different areas such as biometrics, image classification or security. [...]
En els últims anys, les tècniques de detecció i de reconeixement facial han evolucionat molt. Atès que aquest tipus de tècniques tenen moltes aplicacions útils en camps molt diversos com la biometria, la classificació d'imatges o la seguretat, s'han destinat molts esforços tant econòmics com científics per tractar de millorar-les. [...]

2016-06-28
Enginyeria Informàtica [958]  
3.
14 p, 1.1 MB Puesta en correspondencia de imágenes aéreas y un ortomapa / Hernández Jiménez, Sergio ; Ponsa Mussarra, Daniel, dir. (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació) ; Universitat Autònoma de Barcelona. Escola d'Enginyeria
Para facilitar a los bomberos la extinción de incendios se quiere hacer uso de técnicas de visión por computador con el objetivo de detectar elementos sobre un terreno y geolocalizarlos. Este TFG se basa en una manera de llevar a cabo la geolocalización: Poner en correspondencia las imágenes tomadas por un vehículo aéreo no tripulado (UAV) con un ortomapa del cual ya se conocen las coordenadas de cada pixel. [...]
To facilitate firefighters their work we want to make use of computer vision techniques with the aim of detect elements on land and geolocate them. This TFG is based on a way of carrying out geolocation: Put in correspondence images taken by an unmanned aerial vehicle (UAV) with an ortomap which coordinates of each pixel are known. [...]
Per facilitar als bombers l'extinció d'incendis es volen utilitzar tècniques de visió per computador amb l'objectiu de detectar elements sobre un terreny i geolocalitzar-los, Aquest TFG es basa en una manera de portar a terme la geolocalització: Posar en correspondència les imatges preses per un vehicle aeri no tripulat (UAV) amb un ortomapa del qual ja es coneixen les coordenades de cada píxel. [...]

2015-06-29
Enginyeria Informàtica [958]  

Us interessa rebre alertes sobre nous resultats d'aquesta cerca?
Definiu una alerta personal via correu electrònic o subscribiu-vos al canal RSS.