View source for US Patent Application 18141340. CONTRASTIVE CAPTIONING NEURAL NETWORKS simplified abstract

=CONTRASTIVE CAPTIONING NEURAL NETWORKS=


==Organization Name==

[[Google LLC]]


==Inventor(s)==

[[Jiahui Yu of Jersey City NJ (US)]]

[[Zirui Wang of San Francisco CA (US)]]

[[Vijay Vasudevan of Los Altos Hills CA (US)]]

[[Ho Man Yeung of Mountain View CA (US)]]

[[Seyed Mojtaba Seyedhosseini Tarzjani of Foster City CA (US)]]

[[Yonghui Wu of Fremont CA (US)]]

==CONTRASTIVE CAPTIONING NEURAL NETWORKS - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18141340 titled 'CONTRASTIVE CAPTIONING NEURAL NETWORKS

==Simplified Explanation==

- This patent application is about methods, systems, and apparatus for processing multi-modal inputs using contrastive captioning neural networks.
- The invention involves computer programs encoded on computer storage media.
- The purpose is to improve the processing of multi-modal inputs, which are inputs that involve multiple modes of communication such as text, images, and audio.
- The invention utilizes contrastive captioning neural networks, which are a type of artificial intelligence model that can generate captions for images or other visual inputs.
- The patent application covers various aspects of the invention, including the methods, systems, and apparatus used in the processing of multi-modal inputs.
- The invention may have applications in fields such as computer vision, natural language processing, and multimedia analysis.
- The patent application does not provide a specific title for the invention.


==Original Abstract Submitted==

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing multi-modal inputs using contrastive captioning neural networks.