知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

40 records (took 0.019 seconds)

    Regularized iterative collaborative feature learning from web and user behavior data
    2.
    发明授权
    Regularized iterative collaborative feature learning from web and user behavior data 有权

    公开(公告)号：US11042798B2

    公开(公告)日：2021-06-22

    申请号：US15082877

    申请日：2016-03-28

    Applicant: Adobe Inc.

    Inventor： Zhe Lin ,  Jianchao Yang ,  Hailin Jin ,  Chen Fang

    IPC: G06N3/08 ,  G06N5/04 ,  G06N20/00 ,  G06F16/532 ,  G06F16/58 ,  G06N3/04

    Abstract: Certain embodiments involve learning features of content items (e.g., images) based on web data and user behavior data. For example, a system determines latent factors from the content items based on data including a user's text query or keyword query for a content item and the user's interaction with the content items based on the query (e.g., a user's click on a content item resulting from a search using the text query). The system uses the latent factors to learn features of the content items. The system uses a previously learned feature of the content items for iterating the process of learning features of the content items to learn additional features of the content items, which improves the accuracy with which the system is used to learn other features of the content items.

    REINFORCEMENT LEARNING-BASED TECHNIQUES FOR TRAINING A NATURAL MEDIA AGENT
    4.
    发明申请
    REINFORCEMENT LEARNING-BASED TECHNIQUES FOR TRAINING A NATURAL MEDIA AGENT 有权

    公开(公告)号：US20210056408A1

    公开(公告)日：2021-02-25

    申请号：US16549072

    申请日：2019-08-23

    Applicant: Adobe Inc.

    Inventor： Jonathan Brandt ,  Chen Fang ,  Byungmoon Kim ,  Biao Jia

    IPC: G06N3/08 ,  G06N3/04 ,  G09G5/37

    Abstract: The technology described herein is directed to 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.

    CLASSIFYING TERMS FROM SOURCE TEXTS USING IMPLICIT AND EXPLICIT CLASS-RECOGNITION-MACHINE-LEARNING MODELS
    5.
    发明申请
    CLASSIFYING TERMS FROM SOURCE TEXTS USING IMPLICIT AND EXPLICIT CLASS-RECOGNITION-MACHINE-LEARNING MODELS 有权

    公开(公告)号：US20210027141A1

    公开(公告)日：2021-01-28

    申请号：US16518894

    申请日：2019-07-22

    Applicant: Adobe Inc.

    Inventor： Sean MacAvaney ,  Franck Dernoncourt ,  Walter Chang ,  Seokhwan Kim ,  Doo Soon Kim ,  Chen Fang

    IPC: G06N3/04 ,  G06K9/62 ,  G06F17/16 ,  G06F17/15

    Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that can classify term sequences within a source text based on textual features analyzed by both an implicit-class-recognition model and an explicit-class-recognition model. For example, by applying machine-learning models for both implicit and explicit class recognition, the disclosed systems can determine a class corresponding to a particular term sequence within a source text and identify the particular term sequence reflecting the class. The dual-model architecture can equip the disclosed systems to apply (i) the implicit-class-recognition model to recognize implicit references to a class in source texts and (ii) the explicit-class-recognition model to recognize explicit references to the same class in source texts.

    Reinforcement learning-based techniques for training a natural media agent
    7.
    发明授权
    Reinforcement learning-based techniques for training a natural media agent 有权

    公开(公告)号：US11775817B2

    公开(公告)日：2023-10-03

    申请号：US16549072

    申请日：2019-08-23

    Applicant: Adobe Inc.

    Inventor： Jonathan Brandt ,  Chen Fang ,  Byungmoon Kim ,  Biao Jia

    IPC: G06N3/08 ,  G09G5/37 ,  G06N3/04

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

    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.

    Hierarchical scale matching and patch estimation for image style transfer with arbitrary resolution
    8.
    发明授权
    Hierarchical scale matching and patch estimation for image style transfer with arbitrary resolution 有权

    公开(公告)号：US11232547B2

    公开(公告)日：2022-01-25

    申请号：US16930736

    申请日：2020-07-16

    Applicant: Adobe Inc.

    Inventor： Chen Fang ,  Zhe Lin ,  Zhaowen Wang ,  Yulun Zhang ,  Yilin Wang ,  Jimei Yang

    IPC: G06T11/00 ,  G06T5/50 ,  G06T3/40 ,  G06T7/11 ,  G06T3/00

    Abstract: A style of a digital image is transferred to another digital image of arbitrary resolution. A high-resolution (HR) content image is segmented into several low-resolution (LR) patches. The resolution of a style image is matched to have the same resolution as the LR content image patches. Style transfer is then performed on a patch-by-patch basis using, for example, a pair of feature transforms—whitening and coloring. The patch-by-patch style transfer process is then repeated at several increasing resolutions, or scale levels, of both the content and style images. The results of the style transfer at each scale level are incorporated into successive scale levels up to and including the original HR scale. As a result, style transfer can be performed with images having arbitrary resolutions to produce visually pleasing results with good spatial consistency.

    Image captioning utilizing semantic text modeling and adversarial learning
    9.
    发明授权
    Image captioning utilizing semantic text modeling and adversarial learning 有权

    公开(公告)号：US11113599B2

    公开(公告)日：2021-09-07

    申请号：US15630604

    申请日：2017-06-22

    Applicant: Adobe Inc.

    Inventor： Zhaowen Wang ,  Shuai Tang ,  Hailin Jin ,  Chen Fang

    IPC: G06N3/08 ,  G06K9/00 ,  G06N20/00 ,  G06N3/04 ,  G06K9/62

    Abstract: The present disclosure includes methods and systems for generating captions for digital images. In particular, the disclosed systems and methods can train an image encoder neural network and a sentence decoder neural network to generate a caption from an input digital image. For instance, in one or more embodiments, the disclosed systems and methods train an image encoder neural network (e.g., a character-level convolutional neural network) utilizing a semantic similarity constraint, training images, and training captions. Moreover, the disclosed systems and methods can train a sentence decoder neural network (e.g., a character-level recurrent neural network) utilizing training sentences and an adversarial classifier.

    DEEP GENERATION OF USER-CUSTOMIZED ITEMS
    10.
    发明申请
    DEEP GENERATION OF USER-CUSTOMIZED ITEMS 有权

    公开(公告)号：US20210192594A1

    公开(公告)日：2021-06-24

    申请号：US17192713

    申请日：2021-03-04

    Applicant: Adobe Inc. ,  The Regents of the University of California

    Inventor： Chen Fang ,  Zhaowen Wang ,  Wangcheng Kang ,  Julian McAuley

    IPC: G06Q30/06 ,  G06N3/08 ,  G06F16/532

    Abstract: The present disclosure relates to a personalized fashion generation system that synthesizes user-customized images using deep learning techniques based on visually-aware user preferences. In particular, the personalized fashion generation system employs an image generative adversarial neural network and a personalized preference network to synthesize new fashion items that are individually customized for a user. Additionally, the personalized fashion generation system can modify existing fashion items to tailor the fashion items to a user's tastes and preferences.

Patent Agency Ranking