English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This invention lies in the field of digital signal processing. It is a video recognition system of different contents based on deep learning. The invention comprises the following procedures:First,the videos will be uploaded and the system will extract their key frames. After that ,these frames will be sent to the neural network resnet34.The neural network will output the frames categories and a statistics will be made to decide the content of the videos. The models used by our neural network can be trained by the following processes:The videos will be uploaded at first and their key frames will be extracted. These key frames will be used to generate the data set .The neural network resnet34 will be built in the next step and pre-trained models are used. The data set will be used for transform learning and finally we can get the final models. In our test,the accuracy reached about 81.48% after just 25 epochs training. Brieflythis invention can recognize the content of the videos and categorize them. In other words, it is an unattended system. input Convolutional ReLU Max Convolutional Layer Pooling Layer2 ReLU Convolutional ReLU Convolutional Layer3 Layer4 Convolutional Average Fully Layer5 Pooling Layer Layer Relu Reshape Softmax output Figure 1

Unattended Video Classifying System based on Transfer Leaning