公开(公告)号：US20240135197A1

公开(公告)日：2024-04-25

申请号：US17962962

申请日：2022-10-10

Applicant: Adobe Inc.

Inventor： Vishwa VINAY ,  Tirupati Saketh CHANDRA ,  Rishi AGARWAL ,  Kuldeep KULKARNI ,  Hiransh GUPTA ,  Aniruddha MAHAPATRA ,  Vaidehi Ramesh PATIL

IPC: G06N5/02

CPC classification number: G06N5/022

Abstract: Embodiments are disclosed for expanding a seed scene using proposals from a generative model of scene graphs. The method may include clustering subgraphs according to respective one or more maximal connected subgraphs of a scene graph. The scene graph includes a plurality of nodes and edges. The method also includes generating a scene sequence for the scene graph based on the clustered subgraphs. A first machine learning model determines a predicted node in response to receiving the scene sequence. A second machine learning model determines a predicted edge in response to receiving the scene sequence and the predicted node. A scene graph is output according to the predicted node and the predicted edge.

公开(公告)号：US20220180572A1

公开(公告)日：2022-06-09

申请号：US17111819

申请日：2020-12-04

Applicant: ADOBE INC

Inventor： PARIDHI MAHESHWARI ,  Vishwa VINAY ,  Dhananjay RAUT ,  Nihal JAIN ,  Praneetha VADDAMANU ,  Shraiysh VAISHAY

IPC: G06T11/00 ,  G06K9/46 ,  G06K9/62 ,  G06F40/253 ,  G06F40/30 ,  G06N3/04 ,  G06N3/08

Abstract: Systems and methods for color representation are described. Embodiments of the inventive concept are configured to receive an attribute-object pair including a first term comprising an attribute label and a second term comprising an object label, encode the attribute-object pair to produce encoded features using a neural network that orders the first term and the second term based on the attribute label and the object label, and generate a color profile for the attribute-object pair based on the encoded features, wherein the color profile is based on a compositional relationship between the first term and the second term.

公开(公告)号：US20240012849A1

公开(公告)日：2024-01-11

申请号：US17862258

申请日：2022-07-11

Applicant: Adobe Inc.

Inventor： Praneetha VADDAMANU ,  Nihal JAIN ,  Paridhi MAHESHWARI ,  Kuldeep KULKARNI ,  Vishwa VINAY ,  Balaji Vasan SRINIVASAN ,  Niyati CHHAYA ,  Harshit AGRAWAL ,  Prabhat MAHAPATRA ,  Rizurekh SAHA

IPC: G06F16/532 ,  G06V10/74 ,  G06V10/56 ,  G06V10/82 ,  G06V20/30 ,  G06V10/774 ,  G06F16/535

CPC classification number: G06F16/532 ,  G06V10/761 ,  G06V10/56 ,  G06V10/82 ,  G06V20/30 ,  G06V10/774 ,  G06F16/535

Abstract: Embodiments are disclosed for multichannel content recommendation. The method may include receiving an input collection comprising a plurality of images. The method may include extracting a set of feature channels from each of the images. The method may include generating, by a trained machine learning model, an intent channel of the input collection from the set of feature channels. The method may include retrieving, from a content library, a plurality of search result images that include a channel that matches the intent channel. The method may include generating a recommended set of images based on the intent channel and the set of feature channels.

公开(公告)号：US20230141448A1

公开(公告)日：2023-05-11

申请号：US17522790

申请日：2021-11-09

Applicant: Adobe Inc.

Inventor： Suryateja BV ,  Vishwa VINAY ,  Niyati Himanshu CHHAYA ,  Navita GOYAL ,  Elaine CHAO ,  Balaji Vasan SRINIVASAN ,  Aparna GARIMELLA

IPC: G06F40/194 ,  G06F16/93 ,  G06F16/901 ,  G06F40/14

CPC classification number: G06F40/194 ,  G06F16/93 ,  G06F16/9027 ,  G06F40/14

Abstract: Embodiments are disclosed for generating an intelligent change summary are described. In some embodiments, a method of generating an intelligent change summary includes obtaining a representation of a plurality of versions of a document, determining a distance score based on a comparison of a first of version of the document and a second version of the document, the distance score representing a magnitude of changes made from the first version of the document to the second version of the document, and generating a change summary of the document based on the distance score.