Dance Art Scene Classification Based on Convolutional Neural Networks

Abstract

Digital multimedia resources have become an important part of people’s daily cultural life. Automatic scene classification of a large number of dance art videos is the basis for scene semantic based video content retrieval. In order to improve the accuracy of scene classification, the videos are identified using a deep convolutional neural network based on differential evolution for dance art videos. First, the Canny operator is used in YCbCr colour space to detect the human silhouette in the key frames of the video. Then, the AdaBoost algorithm based on cascade structure is used to implement human target tracking and labelling, and the construction and updating of weak classifiers are analysed. Next, a differential evolution algorithm is used to optimise the structural parameters of the convolutional neural network, and an adaptive strategy is adopted for the scaling factor of the differential evolution algorithm to improve the optimisation solution accuracy. Finally, the improved deep convolutional neural network is used to train the classification of the labelled videos in order to obtain stable scene classification results. The experimental results show that by reasonably setting the crossover rate of differential evolution and the convolutional kernel size of the convolutional neural network, high scene classification performance can be obtained. The high accuracy and low root-mean-square error validate the applicability of the proposed method in dance art scene classification.

Classification of dances using AlexNet, ResNet18 and SqueezeNet1_0

“…We can also compare our results with the approach proposed by Li [24]. They utilized a deep CNN model based on differential evolution for their approach to classify dances.…”

Detecção de edições em áudios baseada na análise tempo-frequência e em redes neurais convolucionais

“…O espectrograma da STFT, tanto na escala linear como na escala mel, é uma representação no domínio tempo-frequência particularmente útil devido à natureza não estacionária do sinal sonoro. No entanto, uma representação alternativa derivada da análise tempo-frequência, o espectrograma da transformada Q constante (Constant Q Transform -CQT), foi aplicada com sucesso em diferentes tarefas de processamento de sinais de áudio, como classificação de cenas acústicas [6], classificação de eventos de áudio [9] e detecção de deepfakes [15].…”