Napredna pretraga

Pregled bibliografske jedinice broj: 902373

Multi-label Poster Classification into Genres Using Different Problem Transformation Methods


Pobar, Miran; Ivašić-Kos, Marina
Multi-label Poster Classification into Genres Using Different Problem Transformation Methods // Computer Analysis of Images and Patterns, CAIP 2017, Lecture Notes in Computer Science, vol. 1042 / Felsberg, Michael ; Heyden, Anders ; Krüger, Norbert (ur.).
Ystadu, Švedskoj: Springer, 2017. str. 367-378 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


Naslov
Multi-label Poster Classification into Genres Using Different Problem Transformation Methods

Autori
Pobar, Miran ; Ivašić-Kos, Marina

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Computer Analysis of Images and Patterns, CAIP 2017, Lecture Notes in Computer Science, vol. 1042 / Felsberg, Michael ; Heyden, Anders ; Krüger, Norbert - Ystadu, Švedskoj : Springer, 2017, 367-378

ISBN
978-3-319-64697-8

Skup
CAIP 2017

Mjesto i datum
Ystadu, Švedskoj, 22-24.08.2017

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Multi-label classification RAKEL ensemble method Binary relevance Classifier chains Movie poster Classemes

Sažetak
Classification of movies into genres from the accompanying promotional materials such as posters is a typical multi-label classification problem. Posters usually highlight a movie scene or characters, and at the same time should inform about the genre or the plot of the movie to attract the potential audience, so our assumption was that the relevant information can be captured in visual features. We have used three typical methods for transforming the multi-label problem into a number of single-label problems that can be solved with standard classifiers. We have used the binary relevance, random k-labelsets (RAKEL), and classifier chains with Naïve Bayes classifier as a base classifier. We wanted to compare the classification performance using structural features descriptor extracted from poster images, with the performance obtained using the Classeme feature descriptors that are trained on general images datasets. The classification performance of used transformation methods is evaluated on a poster dataset containing 6000 posters classified into 18 and 11 genres.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Informacijske i komunikacijske znanosti



POVEZANOST RADA


Projekt / tema
HRZZ-IP-06-2016-8345

Ustanove
Sveučilište u Rijeci - Odjel za informatiku