Want to monitor Patent Applications? Get a free weekly report!

Jump to content

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

From WikiPatents

TEXT-AUGMENTED OBJECT CENTRIC RELATIONSHIP DETECTION

Organization Name

ADOBE INC.

Inventor(s)

Ziyan Yang of Houston TX US

Kushal Kafle of Sunnyvale CA US

Zhe Lin of Clyde Hill WA US

Scott Cohen of Cupertino CA US

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.