Sunday, 17 December 2017

Article 67 (160) Movie genre classification: A multi-label approach based on convolutions through time

Movie genre classification: A multi-label approach based on convolutions through time
The task of labeling movies according to their corresponding genre is a challenging classification problem, having in mind that genre is an immaterial feature that cannot be directly pinpointed in any of the movie frames. In this paper, we propose a novel deep neural architecture based on convolutional neural networks for performing multi-label movie-trailer genre classification. We compare the proposed approach with the current state-of-the-art methods for movie classification that employ well-known image descriptors and other low-level handcrafted features. Results show that our method substantially outperforms the state-of-the-art for this task, improving classification performance for all movie genres.


No comments:

Post a Comment