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

In this paper, we build a visual dialogue dataset, named InfoVisDial, whichprovides rich informative answers in each round even with external knowledgerelated to the visual content. Different from existing datasets where theanswer is compact and short, InfoVisDial contains long free-form answers withrich information in each round of dialogue. For effective data collection, thekey idea is to bridge the large-scale multimodal model (e.g., GIT) and thelanguage models (e.g., GPT-3). GIT can describe the image content even withscene text, while GPT-3 can generate informative dialogue based on the imagedescription and appropriate prompting techniques. With such automatic pipeline,we can readily generate informative visual dialogue data at scale. Then, we askhuman annotators to rate the generated dialogues to filter the low-qualityconversations.Human analyses show that InfoVisDial covers informative anddiverse dialogue topics: $54.4\%$ of the dialogue rounds are related to imagescene texts, and $36.7\%$ require external knowledge. Each round's answer isalso long and open-ended: $87.3\%$ of answers are unique with an average lengthof $8.9$, compared with $27.37\%$ and $2.9$ in VisDial. Last, we propose astrong baseline by adapting the GIT model for the visual dialogue task andfine-tune the model on InfoVisDial. Hopefully, our work can motivate moreeffort on this direction.

InfoVisDial: An Informative Visual Dialogue Dataset by Bridging Large Multimodal and Language Models