An examples of multi-modal interactive sessions using Google′s Bard (IMAGE)
Caption
the AI system responds to the user′s question based on images sourced from the Microsoft COCO dataset. In Figs.2–11 from the full text, the expected standard answers are provided in parentheses, except where otherwise stated. Please refer to Sections 2.1–2.5, 2.11, for further details.
Credit
Beijing Zhongke Journal Publising Co. Ltd.
Usage Restrictions
Credit must be given to the creator.
License
CC BY