Machine Learning for Visual Concept Recognition and Ranking for Images

Alexander Binder; Wojciech Samek; Klaus Robert Müller; Motoaki Kawanabe

doi:10.1007/978-3-319-06755-1_17

Machine Learning for Visual Concept Recognition and Ranking for Images

Alexander Binder, Wojciech Samek, Klaus Robert Müller, Motoaki Kawanabe

Research output: Chapter in Book/Report/Conference proceeding › Chapter

1 Citation (Scopus)

Abstract

Recognition of a large set of generic visual concepts in images and ranking of images based on visual semantics is one of the unsolved tasks for future multimedia and scientific applications based on image collections. From that perspective, improvements of the quality of semantic annotations for image data are well matched to the goals of the THESEUS research program with respect to multimedia and scientific services. We will introduce the data-driven and algorithmic challenges inherent in such tasks from a perspective of statistical data analysis and machine learning and discuss approaches relying on kernel-based similarities and discriminative methods which are capable of processing large-scale datasets.

Original language	English
Title of host publication	Towards the Internet of Services The THESEUS Research Program
Publisher	Springer Verlag
Pages	211-223
Number of pages	13
ISBN (Print)	9783319067544
DOIs	https://doi.org/10.1007/978-3-319-06755-1_17
Publication status	Published - 2014

Publication series

Name	Cognitive Technologies
Volume	39
ISSN (Print)	1611-2482

Bibliographical note

Funding Information:
This work was primarily supported by the German Federal Ministry for Economic Affairs and Energy (BMWi) under the THESEUS research program (Grant 01MQ07018). Furthermore it was in part supported by the World Class University Program through the National Research Foundation of Korea funded by the Korean Ministry of Education, Science, and Technology, under Grant R31-10008. We express our thanks to Volker Tresp, the work package leader at CTC WP6, Ralf Schäfer from the Fraunhofer HHI and Shinichi Nakajima from the Nikon corporation for the fruitful collaboration.

ASJC Scopus subject areas

Software
Artificial Intelligence

Access to Document

10.1007/978-3-319-06755-1_17

Cite this

@inbook{946512ba5849416f9d0ac926613ecf4f,

title = "Machine Learning for Visual Concept Recognition and Ranking for Images",

abstract = "Recognition of a large set of generic visual concepts in images and ranking of images based on visual semantics is one of the unsolved tasks for future multimedia and scientific applications based on image collections. From that perspective, improvements of the quality of semantic annotations for image data are well matched to the goals of the THESEUS research program with respect to multimedia and scientific services. We will introduce the data-driven and algorithmic challenges inherent in such tasks from a perspective of statistical data analysis and machine learning and discuss approaches relying on kernel-based similarities and discriminative methods which are capable of processing large-scale datasets.",

author = "Alexander Binder and Wojciech Samek and M{\"u}ller, {Klaus Robert} and Motoaki Kawanabe",

note = "Funding Information: This work was primarily supported by the German Federal Ministry for Economic Affairs and Energy (BMWi) under the THESEUS research program (Grant 01MQ07018). Furthermore it was in part supported by the World Class University Program through the National Research Foundation of Korea funded by the Korean Ministry of Education, Science, and Technology, under Grant R31-10008. We express our thanks to Volker Tresp, the work package leader at CTC WP6, Ralf Sch{\"a}fer from the Fraunhofer HHI and Shinichi Nakajima from the Nikon corporation for the fruitful collaboration.",

year = "2014",

doi = "10.1007/978-3-319-06755-1_17",

language = "English",

isbn = "9783319067544",

series = "Cognitive Technologies",

publisher = "Springer Verlag",

pages = "211--223",

booktitle = "Towards the Internet of Services The THESEUS Research Program",

}

TY - CHAP

T1 - Machine Learning for Visual Concept Recognition and Ranking for Images

AU - Binder, Alexander

AU - Samek, Wojciech

AU - Müller, Klaus Robert

AU - Kawanabe, Motoaki

N1 - Funding Information: This work was primarily supported by the German Federal Ministry for Economic Affairs and Energy (BMWi) under the THESEUS research program (Grant 01MQ07018). Furthermore it was in part supported by the World Class University Program through the National Research Foundation of Korea funded by the Korean Ministry of Education, Science, and Technology, under Grant R31-10008. We express our thanks to Volker Tresp, the work package leader at CTC WP6, Ralf Schäfer from the Fraunhofer HHI and Shinichi Nakajima from the Nikon corporation for the fruitful collaboration.

PY - 2014

Y1 - 2014

N2 - Recognition of a large set of generic visual concepts in images and ranking of images based on visual semantics is one of the unsolved tasks for future multimedia and scientific applications based on image collections. From that perspective, improvements of the quality of semantic annotations for image data are well matched to the goals of the THESEUS research program with respect to multimedia and scientific services. We will introduce the data-driven and algorithmic challenges inherent in such tasks from a perspective of statistical data analysis and machine learning and discuss approaches relying on kernel-based similarities and discriminative methods which are capable of processing large-scale datasets.

AB - Recognition of a large set of generic visual concepts in images and ranking of images based on visual semantics is one of the unsolved tasks for future multimedia and scientific applications based on image collections. From that perspective, improvements of the quality of semantic annotations for image data are well matched to the goals of the THESEUS research program with respect to multimedia and scientific services. We will introduce the data-driven and algorithmic challenges inherent in such tasks from a perspective of statistical data analysis and machine learning and discuss approaches relying on kernel-based similarities and discriminative methods which are capable of processing large-scale datasets.

UR - http://www.scopus.com/inward/record.url?scp=84907340715&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-06755-1_17

DO - 10.1007/978-3-319-06755-1_17

M3 - Chapter

AN - SCOPUS:84907340715

SN - 9783319067544

T3 - Cognitive Technologies

SP - 211

EP - 223

BT - Towards the Internet of Services The THESEUS Research Program

PB - Springer Verlag

ER -

Machine Learning for Visual Concept Recognition and Ranking for Images

Abstract

Publication series

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this