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

Technology videos contain rich multi-modal information. In cross-modalinformation search, the data features of different modalities cannot becompared directly, so the semantic gap between different modalities is a keyproblem that needs to be solved. To address the above problems, this paperproposes a novel Feature Fusion based Adversarial Cross-modal Retrieval method(FFACR) to achieve text-to-video matching, ranking and searching. The proposedmethod uses the framework of adversarial learning to construct a videomultimodal feature fusion network and a feature mapping network as generator, amodality discrimination network as discriminator. Multi-modal features ofvideos are obtained by the feature fusion network. The feature mapping networkprojects multi-modal features into the same semantic space based on semanticsand similarity. The modality discrimination network is responsible fordetermining the original modality of features. Generator and discriminator aretrained alternately based on adversarial learning, so that the data obtained bythe feature mapping network is semantically consistent with the original dataand the modal features are eliminated, and finally the similarity is used torank and obtain the search results in the semantic space. Experimental resultsdemonstrate that the proposed method performs better in text-to-video searchthan other existing methods, and validate the effectiveness of the method onthe self-built datasets of technology videos.

Cross-modal Search Method of Technology Video based on Adversarial Learning and Feature Fusion