Movie genre classification with Convolutional Neural Networks

Simões, Gabriel; Wehrmann, Jônatas; Barros, Rodrigo C.; Ruiz, Duncan D.

doi:10.1109/ijcnn.2016.7727207

Cited by 67 publications

(23 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A convolutional neural network is a class of deep neural network widely used in image processing and computer vision. It has been successfully applied to image recognition [29][30][31][32][33][34], semantic segmentation [35][36][37][38], video analysis [39][40][41][42][43], and many other applications. Its working principle is similar to that of regular multilayer neural networks, but with tied weights wherein only neurons within each local region are fully connected to individual neurons in the next layer, taking advantage of the fact that structural information is contained within local regions of the image, rather than the whole [44].…”

Section: Network Architecturementioning

confidence: 99%

Spatial Resolution Enhancement of Brillouin Optical Correlation-Domain Reflectometry Using Convolutional Neural Network: Proof of Concept

et al. 2021

View full text Add to dashboard Cite

Brillouin optical correlation-domain reflectometry (BOCDR) is a fiber-optic distributed sensing technique with single-end accessibility and high spatial resolution. In BOCDR, the measured Brillouin gain spectrum (BGS) distribution is generally given by a convolution of the intrinsic BGS distribution and the beat-power spectrum. In most conventional implementations, the Brillouin frequency shift (BFS) distribution is directly obtained using the measured BGS distribution. Determining the BFS distribution on the basis of the intrinsic BGS distribution will give potentially higher spatial resolution, which can be achieved by deconvolution of the measured BGS distribution. In this work, we employ a convolutional neural network to perform this deconvolution processing in BOCDR and show its potential for spatial resolution enhancement. A spatial resolution which is 5 times higher than the nominal value is demonstrated.INDEX TERMS Brillouin scattering, convolutional neural network, distributed strain sensing, optical fiber sensing, spatial resolution.

show abstract

Section: Network Architecturementioning

confidence: 99%

Spatial Resolution Enhancement of Brillouin Optical Correlation-Domain Reflectometry Using Convolutional Neural Network: Proof of Concept

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Similar to genre classification using posters, the use of lowlevel features for classification in movie trailers has also been studied [11], [15]. In addition, genre classification based on trailer information has been performed using convolutional neural networks [16]. A trailer dataset for genre classification was created; however, the number of genres was limited to four, and multiple label classification was not addressed.…”

Section: B Non-poster-based Movie Genre Classificationmentioning

confidence: 99%

Poster-Based Multiple Movie Genre Classification Using Inter-Channel Features

Jang

Kim

2020

IEEE Access

View full text Add to dashboard Cite

As the scale of the film industry grows, the demand for well-established movie databases is also growing. The genre of a movie supplies information on its overall content and has multiple values. Therefore, it should be well classified utilizing the characteristics of movies, without omissions in the database. In this study, we extract the optimal information and characteristics from movie posters to aid the classification of movies into genres and propose the use of a Gram layer in a convolutional neural network (CNN). The Gram layer first extracts style features by applying the Gram matrix to produce a feature map of a poster image. Using this as a style weight, the existing feature map is merged with style information to perform the genre classification task. The proposed Gram layer performed multi-genre classification tasks with higher efficiency than a residual neural network (ResNet), which is the current CNN model used for such tasks. We compared the activation map with the Squeeze-and-Excitation network, which gives weight to the image, and we confirmed that the introduction of the Gram layer actually focuses on the style of the movie poster. To classify the movie genres, we reconstructed the poster dataset into 12 multi-genres that emphasized the characteristics of each poster.

show abstract

“…Gabriel et al [1] proposed a model which uses Convolutional Neural Network (CNN) for image processing in order to predict genre from movie trailers. They created a dataset containing trailers of movies and made it public and created a classification method using CNN architecture to classify movies on base of its genres.…”

Section: Previous Workmentioning

confidence: 99%

Movie Genre Prediction Based on Plot Synopsis

Sharma¹

2020

IJMTST

View full text Add to dashboard Cite

Movies have now become one of the main sources of entertainment for people. The extensive use of Internet has increased the creation and sharing of movie related data online. Movie plot summaries generally tell about the movie genres and many people read them before deciding to watch a movie. An automatic system can be applied to predict genres based on summaries. The objective dataset chosen by us consists of 14828 movies taken from Kaggle. We use different approaches such as TFIDF, Char gram, Skip gram etc to get better accuracy scores in predicting movie genre tags.

show abstract

Movie genre classification with Convolutional Neural Networks

Cited by 67 publications

References 26 publications

Spatial Resolution Enhancement of Brillouin Optical Correlation-Domain Reflectometry Using Convolutional Neural Network: Proof of Concept

Spatial Resolution Enhancement of Brillouin Optical Correlation-Domain Reflectometry Using Convolutional Neural Network: Proof of Concept

Poster-Based Multiple Movie Genre Classification Using Inter-Channel Features

Movie Genre Prediction Based on Plot Synopsis

Contact Info

Product

Resources

About