公开(公告)号：US20230214600A1

公开(公告)日：2023-07-06

申请号：US18182068

申请日：2023-03-10

Applicant: Adobe Inc.

Inventor： Zhe LIN ,  Walter W. CHANG ,  Scott COHEN ,  Khoi Viet PHAM ,  Jonathan BRANDT ,  Franck DERNONCOURT

IPC: G06F40/30 ,  G06F16/532 ,  G06F16/55 ,  G06N5/02 ,  G06N5/04 ,  G06F40/205 ,  G06F40/295 ,  G06N20/00

CPC classification number: G06F40/30 ,  G06F16/532 ,  G06F16/55 ,  G06N5/02 ,  G06N5/04 ,  G06F40/205 ,  G06F40/295 ,  G06N20/00

Abstract: Embodiments of the present invention provide systems, methods, and non-transitory computer storage media for parsing a given input referring expression into a parse structure and generating a semantic computation graph to identify semantic relationships among and between objects. At a high level, when embodiments of the preset invention receive a referring expression, a parse tree is created and mapped into a hierarchical subject, predicate, object graph structure that labeled noun objects in the referring expression, the attributes of the labeled noun objects, and predicate relationships (e.g., verb actions or spatial propositions) between the labeled objects. Embodiments of the present invention then transform the subject, predicate, object graph structure into a semantic computation graph that may be recursively traversed and interpreted to determine how noun objects, their attributes and modifiers, and interrelationships are provided to downstream image editing, searching, or caption indexing tasks.

公开(公告)号：US20240037398A1

公开(公告)日：2024-02-01

申请号：US18479486

申请日：2023-10-02

Applicant: Adobe Inc.

Inventor： Jonathan BRANDT ,  Chen FANG ,  Byungmoon KIM ,  Biao JIA

IPC: G06N3/08 ,  G09G5/37 ,  G06N3/04

CPC classification number: G06N3/08 ,  G09G5/37 ,  G06N3/04

Abstract: Some embodiments involve a reinforcement learning based framework for training a natural media agent to learn a rendering policy without human supervision or labeled datasets. The reinforcement learning based framework feeds the natural media agent a training dataset to implicitly learn the rendering policy by exploring a canvas and minimizing a loss function. Once trained, the natural media agent can be applied to any reference image to generate a series (or sequence) of continuous-valued primitive graphic actions, e.g., sequence of painting strokes, that when rendered by a synthetic rendering environment on a canvas, reproduce an identical or transformed version of the reference image subject to limitations of an action space and the learned rendering policy.