首页>
外国专利>
METHOD FOR EXTRACTING FEATURES OF VIDEO USING ENCODERS BASED ON CONVOLUTIONAL NEURAL NETWORK
METHOD FOR EXTRACTING FEATURES OF VIDEO USING ENCODERS BASED ON CONVOLUTIONAL NEURAL NETWORK
展开▼
机译:卷积神经网络的编码器视频特征提取方法
展开▼
页面导航
摘要
著录项
相似文献
摘要
The present invention relates to feature extraction of a video. More specifically, provided is a method for extracting a video feature set using a plurality of encoders based on an artificial neural network, which comprises the steps of: extracting vectors from an input video using a plurality of artificial neural network classifiers; combining the vectors to reduce dimensions; and verifying whether the dimension-reduced vector is in a shape which meets a predetermined purpose in a corresponding application.
展开▼