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.

Základní údaje

Originální název

Visual Descriptors in Methods for Video Hyperlinking

Autoři

GALUŠČÁKOVÁ, Petra (203 Česká republika), Michal BATKO (203 Česká republika, domácí), Jan ČECH (203 Česká republika), Jiří MATAS (203 Česká republika), David NOVÁK (203 Česká republika, domácí) a Pavel PECINA (203 Česká republika)

Vydání

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

Nakladatel

ACM

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

paměťový nosič (CD, DVD, flash disk)

Kód RIV

RIV/00216224:14330/17:00095298

Organizační jednotka

Fakulta informatiky

ISBN

978-1-4503-4701-3

DOI

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

UT WoS

000610413000042

Klíčová slova anglicky

Video retrieval; Hyperlinking; Information retrieval; Image processing

Štítky

core_B, firank_A

Změněno: 27. 4. 2018 11:07, RNDr. Pavel Šmerk, Ph.D.

Anotace

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.

Návaznosti

GBP103/12/G084, projekt VaV

Název: Centrum pro multi-modální interpretaci dat velkého rozsahu

Investor: Grantová agentura ČR, Centrum pro multi-modální interpretaci dat velkého rozsahu

Citovat

GALUŠČÁKOVÁ, Petra, Michal BATKO, Jan ČECH, Jiří MATAS, David NOVÁK a 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, s. 294-300. ISBN 978-1-4503-4701-3. Dostupné z: 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 a 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, s.~294-300. ISBN~978-1-4503-4701-3. Dostupné z: https://dx.doi.org/10.1145/3078971.3079026.

Podrobný výpis o publikaci