中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

26 records (took 0.013 seconds)

    Multi-Modal Differential Search with Real-Time Focus Adaptation
    12.
    发明申请
    Multi-Modal Differential Search with Real-Time Focus Adaptation 审中-公开

    公开(公告)号：US20200380027A1

    公开(公告)日：2020-12-03

    申请号：US16426369

    申请日：2019-05-30

    Applicant: Adobe Inc.

    Inventor： Pranav Vineet Aggarwal ,  Zhe Lin ,  Baldo Antonio Faieta ,  Saeid Motiian

    IPC: G06F16/583 ,  G06N3/08 ,  G06N20/00 ,  G06F16/33 ,  G06F16/538 ,  G06F16/532

    Abstract: Multi-modal differential search with real-time focus adaptation techniques are described that overcome the challenges of conventional techniques in a variety of ways. In one example, a model is trained to support a visually guided machine-learning embedding space that supports visual intuition as to “what” is represented by text. The visually guided language embedding space supported by the model, once trained, may then be used to support visual intuition as part of a variety of functionality. In one such example, the visually guided language embedding space as implemented by the model may be leveraged as part of a multi-modal differential search to support search of digital images and other digital content with real-time focus adaptation which overcomes the challenges of conventional techniques.

    Stylized motion effects
    13.
    发明授权
    Stylized motion effects 有权

    公开(公告)号：US12182955B2

    公开(公告)日：2024-12-31

    申请号：US17814940

    申请日：2022-07-26

    Applicant: ADOBE INC.

    Inventor： Pranav Vineet Aggarwal ,  Alvin Ghouas ,  Ajinkya Gorakhnath Kale

    IPC: G06T5/50 ,  G06T5/77 ,  G06T7/11 ,  G06T7/194 ,  G06T19/20

    Abstract: Systems and methods for image processing are described. Embodiments of the present disclosure receive a first image depicting a scene and a second image that includes a style; segment the first image to obtain a first segment and a second segment, wherein the first segment has a shape of an object in the scene; apply a style transfer network to the first segment and the second image to obtain a first image part, wherein the first image part has the shape of the object and the style from the second image; combine the first image part with a second image part corresponding to the second segment to obtain a combined image; and apply a lenticular effect to the combined image to obtain an output image.

    Text-to-Visual Machine Learning Embedding Techniques
    16.
    发明申请
    Text-to-Visual Machine Learning Embedding Techniques 有权

    公开(公告)号：US20210365727A1

    公开(公告)日：2021-11-25

    申请号：US17398317

    申请日：2021-08-10

    Applicant: Adobe Inc.

    Inventor： Pranav Vineet Aggarwal ,  Zhe Lin ,  Baldo Antonio Faieta ,  Saeid Motiian

    IPC: G06K9/62 ,  G06F16/535 ,  G06N20/00 ,  G06K9/72

    Abstract: Text-to-visual machine learning embedding techniques are described that overcome the challenges of conventional techniques in a variety of ways. These techniques include use of query-based training data which may expand availability and types of training data usable to train a model. Generation of negative digital image samples is also described that may increase accuracy in training the model using machine learning. A loss function is also described that also supports increased accuracy and computational efficiency by losses separately, e.g., between positive or negative sample embeddings a text embedding.

    Text-to-visual machine learning embedding techniques
    17.
    发明授权
    Text-to-visual machine learning embedding techniques 有权

    公开(公告)号：US11144784B2

    公开(公告)日：2021-10-12

    申请号：US16426264

    申请日：2019-05-30

    Applicant: Adobe Inc.

    Inventor： Pranav Vineet Aggarwal ,  Zhe Lin ,  Baldo Antonio Faieta ,  Saeid Motiian

    IPC: G06K9/62 ,  G06K9/72 ,  G06F16/535 ,  G06N20/00 ,  G06F3/0482

    Abstract: Text-to-visual machine learning embedding techniques are described that overcome the challenges of conventional techniques in a variety of ways. These techniques include use of query-based training data which may expand availability and types of training data usable to train a model. Generation of negative digital image samples is also described that may increase accuracy in training the model using machine learning. A loss function is also described that also supports increased accuracy and computational efficiency by losses separately, e.g., between positive or negative sample embeddings a text embedding.

    Text-to-Visual Machine Learning Embedding Techniques
    18.
    发明申请
    Text-to-Visual Machine Learning Embedding Techniques 审中-公开

    公开(公告)号：US20200380298A1

    公开(公告)日：2020-12-03

    申请号：US16426264

    申请日：2019-05-30

    Applicant: Adobe Inc.

    Inventor： Pranav Vineet Aggarwal ,  Zhe Lin ,  Baldo Antonio Faieta ,  Saeid Motiian

    IPC: G06K9/62 ,  G06K9/72 ,  G06F16/535 ,  G06N20/00

    Abstract: Text-to-visual machine learning embedding techniques are described that overcome the challenges of conventional techniques in a variety of ways. These techniques include use of query-based training data which may expand availability and types of training data usable to train a model. Generation of negative digital image samples is also described that may increase accuracy in training the model using machine learning. A loss function is also described that also supports increased accuracy and computational efficiency by losses separately, e.g., between positive or negative sample embeddings a text embedding.

Patent Agency Ranking