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/

Zendy Plus

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

Zendy Tools

Zendy Open

Automatically generating textual descriptions for massive unlabeled images onthe web can greatly benefit realistic web applications, e.g. multimodalretrieval and recommendation. However, existing models suffer from the problemof generating ``over-generic'' descriptions, such as their tendency to generaterepetitive sentences with common concepts for different images. These genericdescriptions fail to provide sufficient textual semantics for ever-changing webimages. Inspired by the recent success of Vision-Language Pre-training (VLP)models that learn diverse image-text concept alignment during pretraining, weexplore leveraging their cross-modal pre-trained knowledge to automaticallyenrich the textual semantics of image descriptions. With no need for additionalhuman annotations, we propose a plug-and-play framework, i.e CapEnrich, tocomplement the generic image descriptions with more semantic details.Specifically, we first propose an automatic data-building strategy to getdesired training sentences, based on which we then adopt prompting strategies,i.e. learnable and template prompts, to incentivize VLP models to generate moretextual details. For learnable templates, we fix the whole VLP model and onlytune the prompt vectors, which leads to two advantages: 1) the pre-trainingknowledge of VLP models can be reserved as much as possible to describe diversevisual concepts; 2) only lightweight trainable parameters are required, so itis friendly to low data resources. Extensive experiments show that our methodsignificantly improves the descriptiveness and diversity of generated sentencesfor web images. The code is available at https://github.com/yaolinli/CapEnrich.

CapEnrich: Enriching Caption Semantics for Web Images via Cross-modal Pre-trained Knowledge