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

Vision and text have been fully explored in contemporary video-textfoundational models, while other modalities such as audio and subtitles invideos have not received sufficient attention. In this paper, we resort toestablish connections between multi-modality video tracks, including Vision,Audio, and Subtitle, and Text by exploring an automatically generatedlarge-scale omni-modality video caption dataset called VAST-27M. Specifically,we first collect 27 million open-domain video clips and separately train avision and an audio captioner to generate vision and audio captions. Then, weemploy an off-the-shelf Large Language Model (LLM) to integrate the generatedcaptions, together with subtitles and instructional prompts into omni-modalitycaptions. Based on the proposed VAST-27M dataset, we train an omni-modalityvideo-text foundational model named VAST, which can perceive and processvision, audio, and subtitle modalities from video, and better support varioustasks including vision-text, audio-text, and multi-modal video-text tasks(retrieval, captioning and QA). Extensive experiments have been conducted todemonstrate the effectiveness of our proposed VAST-27M corpus and VASTfoundation model. VAST achieves 22 new state-of-the-art results on variouscross-modality benchmarks. Code, model and dataset will be released athttps://github.com/TXH-mercury/VAST.

VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset