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

Existed pre-training methods either focus on single-modal tasks ormulti-modal tasks, and cannot effectively adapt to each other. They can onlyutilize single-modal data (i.e. text or image) or limited multi-modal data(i.e. image-text pairs). In this work, we propose a unified-modal pre-trainingarchitecture, namely UNIMO, which can effectively adapt to both single-modaland multi-modal understanding and generation tasks. Large scale of free textcorpus and image collections can be utilized to improve the capability ofvisual and textual understanding, and cross-modal contrastive learning (CMCL)is leveraged to align the textual and visual information into a unifiedsemantic space over a corpus of image-text pairs. As the non-pairedsingle-modal data is very rich, our model can utilize much larger scale of datato learn more generalizable representations. Moreover, the textual knowledgeand visual knowledge can enhance each other in the unified semantic space. Theexperimental results show that UNIMO significantly improves the performance ofseveral single-modal and multi-modal downstream tasks. Our code and pre-trainedmodels are public at the UNIMO project page https://unimo-ptm.github.io/

UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning