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 language pre-training aims to learn alignments between vision andlanguage from a large amount of data. Most existing methods only learnimage-text alignments. Some others utilize pre-trained object detectors toleverage vision language alignments at the object level. In this paper, wepropose to learn multi-grained vision language alignments by a unifiedpre-training framework that learns multi-grained aligning and multi-grainedlocalization simultaneously. Based on it, we present X$^2$-VLM, an all-in-onemodel with a flexible modular architecture, in which we further unifyimage-text pre-training and video-text pre-training in one model. X$^2$-VLM isable to learn unlimited visual concepts associated with diverse textdescriptions. Experiment results show that X$^2$-VLM performs the best on baseand large scale for both image-text and video-text tasks, making a goodtrade-off between performance and model scale. Moreover, we show that themodular design of X$^2$-VLM results in high transferability for it to beutilized in any language or domain. For example, by simply replacing the textencoder with XLM-R, X$^2$-VLM outperforms state-of-the-art multilingualmulti-modal pre-trained models without any multilingual pre-training. The codeand pre-trained models are available at https://github.com/zengyan-97/X2-VLM.

X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks