中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

11 records (took 0.019 seconds)

    ENCODING IMAGE VALUES THROUGH ATTRIBUTE CONDITIONING
    3.
    发明申请
    ENCODING IMAGE VALUES THROUGH ATTRIBUTE CONDITIONING 有权

    公开(公告)号：US20250117970A1

    公开(公告)日：2025-04-10

    申请号：US18637654

    申请日：2024-04-17

    Applicant: ADOBE INC.

    Inventor： Sachin Madhav Kelkar ,  Hareesh Ravi ,  Ritiz Tambi ,  Ajinkya Gorakhnath Kale

    IPC: G06T11/00

    Abstract: A method, apparatus, non-transitory computer readable medium, and system for image generation include obtaining a text prompt and a conditioning attribute. The text prompt is encoded to obtain a text embedding. The conditioning attribute is encoded to obtain an attribute embedding. Then a synthesized image is generated using an image generation model based on the text embedding and the attribute embedding. The synthesized image has the conditioning attribute and depicts an element of the text prompt.

    UPSIDE-DOWN REINFORCEMENT LEARNING FOR IMAGE GENERATION MODELS
    4.
    发明申请
    UPSIDE-DOWN REINFORCEMENT LEARNING FOR IMAGE GENERATION MODELS 有权

    公开(公告)号：US20250117967A1

    公开(公告)日：2025-04-10

    申请号：US18443590

    申请日：2024-02-16

    Applicant: ADOBE INC.

    Inventor： Ritiz Tambi ,  Purvak Lapsiya ,  Ajinkya Gorakhnath Kale ,  Pranav Vineet Aggarwal ,  Nikolaos Vlassis

    IPC: G06T11/00 ,  G06F40/166 ,  G06V10/764

    Abstract: A method, apparatus, non-transitory computer readable media, and system for image generation include obtaining an input text prompt and an indication of a level of a target characteristic, where the target characteristic comprises a characteristic used to train an image generation model. Some embodiments generate an augmented text prompt comprising the input text and an objective text corresponding to the level of the target characteristic. Some embodiments generate, using the image generation model, an image based on the augmented text prompt, where the image depicts content of the input text prompt and has the level of the target characteristic.

    GENERATIVE PROMPT EXPANSION FOR IMAGE GENERATION
    5.
    发明公开
    GENERATIVE PROMPT EXPANSION FOR IMAGE GENERATION 审中-公开

    公开(公告)号：US20240095275A1

    公开(公告)日：2024-03-21

    申请号：US17933595

    申请日：2022-09-20

    Applicant: ADOBE INC.

    Inventor： Ritiz Tambi ,  Ajinkya Gorakhnath Kale

    IPC: G06F16/532

    CPC classification number: G06F16/532

    Abstract: Systems and methods for query processing are described. Embodiments of the present disclosure identify an original query; generate a plurality of expanded queries by generating a plurality of additional phrases based on the original query using a causal language model (CLM) and augmenting the original query with each of the plurality of additional phrases, respectively; and provide a plurality of images in response to the original query, wherein the plurality of images are associated with the plurality of expanded queries, respectively.

    MULTI-LINGUAL TAGGING FOR DIGITAL IMAGES
    6.
    发明申请
    MULTI-LINGUAL TAGGING FOR DIGITAL IMAGES 有权

    公开(公告)号：US20220138439A1

    公开(公告)日：2022-05-05

    申请号：US17088847

    申请日：2020-11-04

    Applicant: Adobe Inc.

    Inventor： Ritiz Tambi ,  Pranav Aggarwal ,  Ajinkya Kale

    IPC: G06F40/58 ,  G06F40/117

    Abstract: Introduced here is an approach to translating tags assigned to digital images. As an example, embeddings may be extracted from a tag to be translated and the digital image with which the tag is associated by a multimodal model. These embeddings can be compared to embeddings extracted from a set of target tags associated with a target language by the multimodal model. Such an approach allows similarity to be established along two dimensions, which ensures the obstacles associated with direct translation can be avoided.

    Generative prompt expansion for image generation
    7.
    发明授权
    Generative prompt expansion for image generation 有权

    公开(公告)号：US12153619B2

    公开(公告)日：2024-11-26

    申请号：US17933595

    申请日：2022-09-20

    Applicant: ADOBE INC.

    Inventor： Ritiz Tambi ,  Ajinkya Gorakhnath Kale

    IPC: G06F16/00 ,  G06F16/532

    Abstract: Systems and methods for query processing are described. Embodiments of the present disclosure identify an original query; generate a plurality of expanded queries by generating a plurality of additional phrases based on the original query using a causal language model (CLM) and augmenting the original query with each of the plurality of additional phrases, respectively; and provide a plurality of images in response to the original query, wherein the plurality of images are associated with the plurality of expanded queries, respectively.

    ZERO-SHOT ENTITY-AWARE NEAREST NEIGHBORS RETRIEVAL
    9.
    发明公开
    ZERO-SHOT ENTITY-AWARE NEAREST NEIGHBORS RETRIEVAL 审中-公开

    公开(公告)号：US20240104131A1

    公开(公告)日：2024-03-28

    申请号：US17934690

    申请日：2022-09-23

    Applicant: ADOBE INC.

    Inventor： Ritiz Tambi ,  Ajinkya Gorakhnath Kale

    IPC: G06F16/532 ,  G06F40/284 ,  G06F40/289

    CPC classification number: G06F16/532 ,  G06F40/284 ,  G06F40/289

    Abstract: Systems and methods for query processing are described. Embodiments of the present disclosure identify a target phrase in an original query, wherein the target phrase comprises a phrase to be replaced in the original query; replace the target phrase with a mask token to obtain a modified query; generate an alternative query based on the modified query using a masked language model (MLM), wherein the alternative query includes an alternative phrase in place of the target phrase that is consistent with a context of the target phrase; and retrieve a search result based on the alternative query.

Patent Agency Ranking