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

There have been many attempts to build multimodal dialog systems that canrespond to a question about given audio-visual information, and therepresentative task for such systems is the Audio Visual Scene-Aware Dialog(AVSD). Most conventional AVSD models adopt the Convolutional Neural Network(CNN)-based video feature extractor to understand visual information. While aCNN tends to obtain both temporally and spatially local information, globalinformation is also crucial for boosting video understanding because AVSDrequires long-term temporal visual dependency and whole visual information. Inthis study, we apply the Transformer-based video feature that can capture bothtemporally and spatially global representations more efficiently than theCNN-based feature. Our AVSD model with its Transformer-based feature attainshigher objective performance scores for answer generation. In addition, ourmodel achieves a subjective score close to that of human answers in DSTC10. Weobserved that the Transformer-based visual feature is beneficial for the AVSDtask because our model tends to correctly answer the questions that need atemporally and spatially broad range of visual information.

Audio Visual Scene-Aware Dialog Generation with Transformer-based Video Representations