Multi-label Classification of Movie Posters into Genres with Rakel Ensemble Method (CROSBI ID 656498)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Ivašić-Kos, Marina ; Pobar, Miran
engleski
Multi-label Classification of Movie Posters into Genres with Rakel Ensemble Method
Movies can belong to more than one genre, so the problem of determining the genres of a movie from its poster is a multi-label classification problem. To solve the multi- label problem, we have used the RAKEL ensemble method along with three typical single-label base classification methods: Naïve Bayes, C4.5 decision tree, and k-NN. The RAKEL method strives to overcome the problem of computational cost and power set label explosion by breaking the initial set of labels into several small-sized label sets. The classification performance of base classifiers on different feature sets is evaluated using multi-label evaluation measures on poster dataset containing 6000 posters classified into 18 and 11 genres. Keeping this in mind, we wanted to examine how different visual feature sets, extracted from poster images, are related to the performance of automatic detection of movie genres, as well as compare it to the performance obtained with the Classeme feature descriptors trained on the datasets of general images.
Multi-label classification ; RAKEL ensemble method ; Movie poster ; Classemes ; GIST
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
370-383.
2017.
objavljeno
10.1007/978-3-319-71078-5_31
Podaci o matičnoj publikaciji
Artificial Intelligence XXXIV. SGAI 2017. Lecture Notes in Computer Science, vol 10630
Bramer, M. ; Petridis, M.
Cham: Springer
978-3-319-71077-8
Podaci o skupu
AI-2017 Thirty-seventh SGAI International Conference on Artificial Intelligence
predavanje
12.12.2017-14.12.2017
Cambridge, Ujedinjeno Kraljevstvo
Povezanost rada
Informacijske i komunikacijske znanosti, Računarstvo