RUO Home

Repositorio Institucional de la Universidad de Oviedo

View Item 
  •   RUO Home
  • Producción Bibliográfica de UniOvi: RECOPILA
  • Capítulos de libros
  • View Item
  •   RUO Home
  • Producción Bibliográfica de UniOvi: RECOPILA
  • Capítulos de libros
  • View Item
    • español
    • English
JavaScript is disabled for your browser. Some features of this site may not work without it.

Browse

All of RUOCommunities and CollectionsBy Issue DateAuthorsTitlesSubjectsxmlui.ArtifactBrowser.Navigation.browse_issnAuthor profilesThis CollectionBy Issue DateAuthorsTitlesSubjectsxmlui.ArtifactBrowser.Navigation.browse_issn

My Account

LoginRegister

Statistics

View Usage Statistics

RECENTLY ADDED

Last submissions
Repository
How to publish
Resources
FAQs

Combining Deep Learning and Preference Learning for Object Tracking

Author:
Pang, Shuchao; Coz Velasco, Juan José delUniovi authority; Zhezhou, Yu; Luaces Rodríguez, ÓscarUniovi authority; Díez Peláez, JorgeUniovi authority
Subject:

Deep learning

Preference learning

Object tracking

Publication date:
2016
Editorial:

Springer

Publisher version:
http://dx.doi.org/10.1007/978-3-319-46675-0_8
Citación:
In: Hirose A., Ozawa S., Doya K., Ikeda K., Lee M., Liu D. (eds) Neural Information Processing. ICONIP 2016. Lecture Notes in Computer Science, vol 9949. Springer, Cham; doi: 10.1007/978-3-319-46675-0_8
Serie:

Lecture Notes in Computer Science;9949

Descripción física:
p. 70-77
Abstract:

Object tracking is nowadays a hot topic in computer vision. Generally speaking, its aim is to find a target object in every frame of a video sequence. In order to build a tracking system, this paper proposes to combine two different learning frameworks: deep learning and preference learning. On the one hand, deep learning is used to automatically extract latent features for describing the multi-dimensional raw images. Previous research has shown that deep learning has been successfully applied in different computer vision applications. On the other hand, object tracking can be seen as a ranking problem, in the sense that the regions of an image can be ranked according to their level of overlapping with the target object. Preference learning is used to build the ranking function. The experimental results of our method, called DPL2DPL2(Deep & Preference Learning), are competitive with respect to the state-of-the-art algorithms

Object tracking is nowadays a hot topic in computer vision. Generally speaking, its aim is to find a target object in every frame of a video sequence. In order to build a tracking system, this paper proposes to combine two different learning frameworks: deep learning and preference learning. On the one hand, deep learning is used to automatically extract latent features for describing the multi-dimensional raw images. Previous research has shown that deep learning has been successfully applied in different computer vision applications. On the other hand, object tracking can be seen as a ranking problem, in the sense that the regions of an image can be ranked according to their level of overlapping with the target object. Preference learning is used to build the ranking function. The experimental results of our method, called DPL2DPL2(Deep & Preference Learning), are competitive with respect to the state-of-the-art algorithms

Description:

International Conference on Neural Information Processing, ICONIP 2016 (23th. 2016. Kyoto, Japan)

URI:
http://hdl.handle.net/10651/39351
ISBN:
978-3-319-46674-3; 978-3-319-46675-0
DOI:
10.1007/978-3-319-46675-0_8
Patrocinado por:

This work was funded by Ministerio de Economía y Competitividad de Españna (grant TIN2015-65069-C2-2-R), Specialized Research Fund for the Doctoral Program of Higher Education of China (grant 20120061110045) and the Project of Science and Technology Development Plan of Jilin Province, China (grant 20150204007GX)

Collections
  • Capítulos de libros [6535]
  • Informática [875]
  • Investigaciones y Documentos OpenAIRE [8421]
Files in this item
Thumbnail
untranslated
Postprint (418.7Kb)
Métricas
Compartir
Exportar a Mendeley
Estadísticas de uso
Estadísticas de uso
Metadata
Show full item record
Página principal Uniovi

Biblioteca

Contacto

Facebook Universidad de OviedoTwitter Universidad de Oviedo
The content of the Repository, unless otherwise specified, is protected with a Creative Commons license: Attribution-Non Commercial-No Derivatives 4.0 Internacional
Creative Commons Image