Two Stage Video Classification Approach Using Convolution Neural Network

This research study focuses on video categorization, which is a crucial area of computer vision with uses in entertainment, education, and surveillance. Convolutional Neural Networks (CNNs) are used in a two-stage approach in the suggested methodology. The video is first broken down into frames, which are subsequently supplied into a CNN model. Another CNN model that predicts the video class uses the output from this model as input. A publicly accessible dataset is used to assess the efficacy of this approach, demonstrating its competitive accuracy performance in comparison to the most advanced techniques. The outcomes indicate that the technique can effectively classify videos and has the potential to be used in a variety of real-world scenarios.