[ Skip to the content ]

Institute of Formal and Applied Linguistics

at Faculty of Mathematics and Physics, Charles University, Prague, Czech Republic


[ Back to the navigation ]

Publication


Year 2015
Type in proceedings without ISBN
Status published
Language English
Author(s) Galuščáková, Petra Pecina, Pavel
Title CUNI at MediaEval 2015 Search and Anchoring in Video Archives: Anchoring via Information Retrieval
Czech title CUNI na MediaEval 2015 Search and Anchoring in Video Archives: Riešenie úlohy Anchoring pomocou metód Information Retrieval
Proceedings 2015: Aachen, Germany: MediaEval 2015: Working Notes Proceedings of the MediaEval 2015 Workshop
How published online
URL http://sunsite.informatik.rwth-aachen.de/Publications/CEUR-WS/Vol-1436/Paper67.pdf
Supported by 2012-2018 GBP103/12/G084 (Centrum pro multi-modální interpretaci dat velkého rozsahu) 2013-2014 GAUK 9209/2013 (Interaktívne spôsoby vyhľadávania v audiovizuálnych dialógových korpusoch) 2015 SVV 260 224 (Teoretické základy informatiky a výpočetní lingvistiky) 2012-2016 PRVOUK P46 (Informatika)
Czech abstract V článku sa venujeme automatickej detekcii anchoring segmentov v kolekcii televíznych programov. Nájdené anchoring segmenty by mali byť ďalej použité pri následnom vyhľadávaní príbuzných segmentov v kolekcii. Anchoring segmenty by mali byť preto pútavé pre používateľov video kolekcie. S využitím linkov odkazujúcich z anchoring segmentov môžu užívatelia prechádzať kolekciu a nájsť ďalšie informácie, ktoré ich zaujímajú. V článku popisujeme dva prístupy - jeden založený na metadatách, druhý na frekvencii vlastných mien a čísloviek nachádzajúcich sa v segmente.
English abstract In the paper we deal with automatic detection of anchoring segments in a collection of TV programmes. The anchoring segments are intended to be further used as a basis for subsequent hyperlinking to another related video segments. The anchoring segments are therefore supposed to be fetching for the users of the collection. Using the hyperlinks, the users can easily navigate through the collection and find more information about the topic of their interest. We present two approaches, one based on metadata, the second one based on frequencies of proper names and numbers contained in the segments. Both approaches proved to be helpful for different aspects of anchoring problem: the segments which contain a large number of proper names and numbers are interesting for the users, while the segments most similar to the video description are highly informative.
Specialization computer science ("informatika")
Confidentiality default – not confidential
Open access no
Editor(s)* Martha A. Larson; Bogdan Ionescu; Mats Sjöberg; Xavier Anguera; Johann Poignant; Michael Riegler; Maria Eskevich; Claudia Hauff; Richard Sutcliffe; Gareth J.F. Jones; Yi-Hsuan Yang; Mohammad Soleymani; Symeon Papadopoulos
ISSN* 1613-0073
Address* Aachen, Germany
Month* September
Publisher* CEUR-WS.org
Institution* TU Delft
Creator: Common Account
Created: 10/9/15 12:19 AM
Modifier: Almighty Admin
Modified: 2/8/16 9:52 PM
***

Content, Design & Functionality: ÚFAL, 2006–2016. Page generated: Wed Jul 18 02:57:32 CEST 2018

[ Back to the navigation ] [ Back to the content ]

100% OpenAIRE compliant