View source for 18470778. TEXT-AUGMENTED OBJECT CENTRIC RELATIONSHIP DETECTION (ADOBE INC.)

=TEXT-AUGMENTED OBJECT CENTRIC RELATIONSHIP DETECTION=


==Organization Name==

[[:Category:ADOBE INC.|ADOBE INC.]]


[[Category:ADOBE INC.]]

==Inventor(s)==

[[:Category:Ziyan Yang of Houston TX US|Ziyan Yang of Houston TX US]][[Category:Ziyan Yang of Houston TX US]]

[[:Category:Kushal Kafle of Sunnyvale CA US|Kushal Kafle of Sunnyvale CA US]][[Category:Kushal Kafle of Sunnyvale CA US]]

[[:Category:Zhe Lin of Clyde Hill WA US|Zhe Lin of Clyde Hill WA US]][[Category:Zhe Lin of Clyde Hill WA US]]

[[:Category:Scott Cohen of Cupertino CA US|Scott Cohen of Cupertino CA US]][[Category:Scott Cohen of Cupertino CA US]]

[[:Category:Zhihong Ding of Davis CA US|Zhihong Ding of Davis CA US]][[Category:Zhihong Ding of Davis CA US]]

==TEXT-AUGMENTED OBJECT CENTRIC RELATIONSHIP DETECTION==


This abstract first appeared for US patent application 18470778 titled 'TEXT-AUGMENTED OBJECT CENTRIC RELATIONSHIP DETECTION

==Original Abstract Submitted==

A method, apparatus, and non-transitory computer readable medium for image processing are described. Embodiments of the present disclosure obtain an image and an input text including a subject from the image and a location of the subject in the image. An image encoder encodes the image to obtain an image embedding. A text encoder encodes the input text to obtain a text embedding. An image processing apparatus based on the present disclosure generates an output text based on the image embedding and the text embedding. In some examples, the output text includes a relation of the subject to an object from the image and a location of the object in the image.



[[Category:G06V20/70]]
[[Category:G06F40/205]]
[[Category:G06V10/25]]
[[Category:G06V10/774]]
[[Category:CPC_G06V20/70]]