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.