Baseline Performance of Pre-trained Models on Movie Genre Classification from Spectrograms
Porawat Visutsak, Kavin Treeraphapkajondet, Visaroot Sakphet, Wachirawit Nitinuntatip, Pawwinkan Satthong, Tanajak Tongbai, Duongduen Ongrungruaeng, Atiwitch Juntra, Watcharaporn Aiamlamai, Issares Sungwanna, Prapaporn Phetrak, Ponrudee Netisopakul, Keun Ho Ryu · ECTI Transactions on Computer and Information Technology (ECTI-CIT) · 2025
This study investigates the use of deep learning for classifying movie genres based on audio spectrograms. We construct a dataset of movie trailers, transform them into spectrograms, and label them by genre. Then, we utilize MATLAB's pre-trained convolutional neural networks (CNNs) for clas- sication, comparing the performance of 9 different architectures, including MobileNet-v2, RestNet-18, DenseNet-201, Places365-GoogLeNet, VGG- 16, VGG-19, Inception-RestNet-v2, Inception-v3, and NASANet-Mobile. We evaluated all models based on their ability to classify movie trailers into ve genres: action, romance, drama, comedy, and thriller. Our results, based on accuracy and F1-score across genres, indicate that VGG16 achieves the highest overall performance with an accuracy of 86.27%, an F1-score of 86.69%, a recall of 86.87%, and a precision of 87.28%. This research demonstrates the potential of leveraging pre-trained CNNs, particularly VGG-16, for efficient and effective audio-based genre classification in movie trailers.