Brno University of Technology at MediaEval 2011 Genre Tagging Task

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F11%3APU97855" target="_blank" >RIV/00216305:26230/11:PU97855 - isvavai.cz</a>

Výsledek na webu

<a href="http://ceur-ws.org/Vol-807/Hradis_BUT_Genre_me11wn.pdf" target="_blank" >http://ceur-ws.org/Vol-807/Hradis_BUT_Genre_me11wn.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Brno University of Technology at MediaEval 2011 Genre Tagging Task

Popis výsledku v původním jazyce

This paper briefly describes our approach to the video genre tagging task which was a part of MediaEval 2011. We focused mainly on visual and audio information, and we exploited metadata and automatic speech transcripts only in a very basic way. Our approach relied on classification and on classifier fusion to combine different sources of information. We did not use any additional training data except the very small exemplary set provided by MediaEval (only 246 videos). The best performance was achievedby metadata alone. Combination with the other sources of information did not improve results in the submitted runs. This was achieved later by choosing more suitable weights in fusion. Excluding the metadata, audio and video gave better results than speech transcripts. Using classifiers for 345 semantic classes from TRECVID 2011 semantic indexing (SIN) task to project the data worked better than classifying directly from video and audio features.

Název v anglickém jazyce

Brno University of Technology at MediaEval 2011 Genre Tagging Task

Popis výsledku anglicky

This paper briefly describes our approach to the video genre tagging task which was a part of MediaEval 2011. We focused mainly on visual and audio information, and we exploited metadata and automatic speech transcripts only in a very basic way. Our approach relied on classification and on classifier fusion to combine different sources of information. We did not use any additional training data except the very small exemplary set provided by MediaEval (only 246 videos). The best performance was achievedby metadata alone. Combination with the other sources of information did not improve results in the submitted runs. This was achieved later by choosing more suitable weights in fusion. Excluding the metadata, audio and video gave better results than speech transcripts. Using classifiers for 345 semantic classes from TRECVID 2011 semantic indexing (SIN) task to project the data worked better than classifying directly from video and audio features.

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

<a href="/cs/project/7E11024" target="_blank" >7E11024: Together Anywhere, Together Anytime - Enlarged European Union</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>Z - Vyzkumny zamer (s odkazem do CEZ)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2011

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Working Notes Proceedings of the MediaEval 2011 Workshop

ISBN

—

ISSN

1613-0073

e-ISSN

—

Počet stran výsledku

2

Strana od-do

1-2

Název nakladatele

CEUR-WS.org

Místo vydání

Pisa, Italy

Místo konání akce

Pisa, Itálie

Datum konání akce

29. 7. 2011

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—