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 explore an efficient approach to establish a foundational video-textmodel. We present VideoCoCa that maximally reuses a pretrained image-textcontrastive captioner (CoCa) model and adapt it to video-text tasks withminimal extra training. While previous works adapt image-text models withvarious cross-frame fusion modules, we find that the generative attentionalpooling and contrastive attentional pooling layers in CoCa are instantlyadaptable to flattened frame embeddings, yielding state-of-the-art results onzero-shot video classification and zero-shot text-to-video retrieval.Furthermore, we explore lightweight finetuning on top of VideoCoCa, and achievestrong results on video question-answering and video captioning.

VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners