Visual Descriptors in Methods for Video Hyperlinking

D 2017

Visual Descriptors in Methods for Video Hyperlinking

GALUŠČÁKOVÁ, Petra, Michal BATKO, Jan ČECH, Jiří MATAS, David NOVÁK et. al.

Basic information

Original name

Visual Descriptors in Methods for Video Hyperlinking

Authors

GALUŠČÁKOVÁ, Petra (203 Czech Republic), Michal BATKO (203 Czech Republic, belonging to the institution), Jan ČECH (203 Czech Republic), Jiří MATAS (203 Czech Republic), David NOVÁK (203 Czech Republic, belonging to the institution) and Pavel PECINA (203 Czech Republic)

Edition

New York, NY, USA, Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval, p. 294-300, 7 pp. 2017

Publisher

ACM

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

storage medium (CD, DVD, flash disk)

RIV identification code

RIV/00216224:14330/17:00095298

Organization unit

Faculty of Informatics

ISBN

978-1-4503-4701-3

DOI

http://dx.doi.org/10.1145/3078971.3079026

UT WoS

000610413000042

Keywords in English

Video retrieval; Hyperlinking; Information retrieval; Image processing

Abstract

V originále

In this paper, we survey different state-of-the-art visual processing methods and utilize them in hyperlinking. Visual information, calculated using Features Signatures, SIMILE descriptors and convolutional neural networks (CNN), is utilized as similarity between video frames and used to find similar faces, objects and setting. Visual concepts in frames are also automatically recognized and textual output of the recognition is combined with search based on subtitles and transcripts. All presented experiments were performed in the Search and Hyperlinking 2014 MediaEval task and Video Hyperlinking 2015 TRECVid task.

Links

GBP103/12/G084, research and development project

Name: Centrum pro multi-modální interpretaci dat velkého rozsahu

Investor: Czech Science Foundation

Citovat

GALUŠČÁKOVÁ, Petra, Michal BATKO, Jan ČECH, Jiří MATAS, David NOVÁK and Pavel PECINA. Visual Descriptors in Methods for Video Hyperlinking. In Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval. New York, NY, USA: ACM, 2017, p. 294-300. ISBN 978-1-4503-4701-3. Available from: https://dx.doi.org/10.1145/3078971.3079026.

@inproceedings{1400884,
   author = {Galuščáková, Petra and Batko, Michal and Čech, Jan and Matas, Jiří and Novák, David and Pecina, Pavel},
   address = {New York, NY, USA},
   booktitle = {Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval},
   doi = {http://dx.doi.org/10.1145/3078971.3079026},
   keywords = {Video retrieval; Hyperlinking; Information retrieval; Image processing},
   howpublished = {paměťový nosič},
   language = {eng},
   location = {New York, NY, USA},
   isbn = {978-1-4503-4701-3},
   pages = {294-300},
   publisher = {ACM},
   title = {Visual Descriptors in Methods for Video Hyperlinking},
   year = {2017}
}

TY  - JOUR
ID  - 1400884
AU  - Galuščáková, Petra - Batko, Michal - Čech, Jan - Matas, Jiří - Novák, David - Pecina, Pavel
PY  - 2017
TI  - Visual Descriptors in Methods for Video Hyperlinking
PB  - ACM
CY  - New York, NY, USA
SN  - 9781450347013
KW  - Video retrieval
KW  - Hyperlinking
KW  - Information retrieval
KW  - Image processing
N2  - In this paper, we survey different state-of-the-art visual processing methods and utilize them in hyperlinking. Visual information, calculated using Features Signatures, SIMILE descriptors and convolutional neural networks (CNN), is utilized as similarity between video frames and used to find similar faces, objects and setting. Visual concepts in frames are also automatically recognized and textual output of the recognition is combined with search based on subtitles and transcripts. All presented experiments were performed in the Search and Hyperlinking 2014 MediaEval task and Video Hyperlinking 2015 TRECVid task.
ER  -

GALUŠČÁKOVÁ, Petra, Michal BATKO, Jan ČECH, Jiří MATAS, David NOVÁK and Pavel PECINA. Visual Descriptors in Methods for Video Hyperlinking. In \textit{Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval}. New York, NY, USA: ACM, 2017, p.~294-300. ISBN~978-1-4503-4701-3. Available from: https://dx.doi.org/10.1145/3078971.3079026.

Detailed Information on Publication Record