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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Thumbnail is the face of online videos. The explosive growth of videos bothin number and variety underpins the importance of a good thumbnail because itsaves potential viewers time to choose videos and even entice them to click onthem. A good thumbnail should be a frame that best represents the content of avideo while at the same time capturing viewers' attention. However, thetechniques and models in the past only focus on frames within a video, and webelieve such narrowed focus leave out much useful information that are part ofa video. In this paper, we expand the definition of content to include title,description, and audio of a video and utilize information provided by thesemodalities in our selection model. Specifically, our model will first sampleframes uniformly in time and return the top 1,000 frames in this subset withthe highest aesthetic scores by a Double-column Convolutional Neural Network,to avoid the computational burden of processing all frames in downstream task.Then, the model incorporates frame features extracted from VGG16, text featuresfrom ELECTRA, and audio features from TRILL. These models were selected becauseof their results on popular datasets as well as their competitive performances.After feature extraction, the time-series features, frames and audio, will befed into Transformer encoder layers to return a vector representing theircorresponding modality. Each of the four features (frames, title, description,audios) will pass through a context gating layer before concatenation. Finally,our model will generate a vector in the latent space and select the frame thatis most similar to this vector in the latent space. To the best of ourknowledge, we are the first to propose a multi-modal deep learning model toselect video thumbnail, which beats the result from the previousState-of-The-Art models.

A Multi-modal Deep Learning Model for Video Thumbnail Selection