Create a Model to Detect Audiovisual Videos by Breaking Down Superscribing Tensor and Using Less Frequency and a Lower Ranking

Abstract

The aim of this study is to develop a model for audiovisual video detection by decomposing superscribing tensors and using reduced frequency and lower rank. This model will be used for identifying videos that have audio with low frequencies and visual frames with low rankings. The proposed model would use a convolutional neural network (CNN) and a recurrent neural network (RNN) to detect and classify the audiovisual characteristics. The Convolutional Neural Network (CNN) will be used to record the video frames with high frequency, while the Recurrent Neural Network (RNN) will be utilised to capture the audio characteristics with low frequency. The training process will use an extensive dataset of audiovisual videos. The performance of the model will be assessed by testing it using a validation dataset. Ultimately, the model will be used in a live setting to identify audiovisual recordings with low occurrence rates.