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

We propose a new two-stage pre-training framework for video-to-textgeneration tasks such as video captioning and video question answering: Agenerative encoder-decoder model is first jointly pre-trained on massiveimage-text data to learn fundamental vision-language concepts, and then adaptedto video data in an intermediate video-text pre-training stage to learnvideo-specific skills such as spatio-temporal reasoning. As a result, ourVideoOFA model achieves new state-of-the-art performance on four VideoCaptioning benchmarks, beating prior art by an average of 9.7 points in CIDErscore. It also outperforms existing models on two open-ended Video QuestionAnswering datasets, showcasing its generalization capability as a universalvideo-to-text model.

VideoOFA: Two-Stage Pre-Training for Video-to-Text Generation