中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

12 records (took 0.015 seconds)

    GENERATING THEME-BASED FOLDERS BY CLUSTERING DIGITAL IMAGES IN A SEMANTIC SPACE
    1.
    发明申请
    GENERATING THEME-BASED FOLDERS BY CLUSTERING DIGITAL IMAGES IN A SEMANTIC SPACE 有权

    公开(公告)号：US20210263970A1

    公开(公告)日：2021-08-26

    申请号：US17314651

    申请日：2021-05-07

    Applicant: Adobe Inc.

    Inventor： Jonas Dahl ,  Sudheer Tumu ,  Nithyanand Kota ,  Mihir Naware ,  Maneesh Dewan ,  Jatin Chhugani ,  Ganesh Satish Mallya

    IPC: G06F16/906 ,  G06K9/46 ,  G06N3/02 ,  G06F16/16

    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for clustering media items in a semantic space to generate theme-based folders that organize media items by content theme. In particular, the disclosed systems can access media items that are stored in an original folder structure. The disclosed systems can generate content-based tags for each media item in a collection of media items. Based on the generated tags, the disclosed systems can map the collection of media items to a semantic space and cluster the collection of media items. The disclosed systems determine themes for the clusters based on the generated tags. The disclosed systems can present a media item navigation graphical user interface comprising the collection of media items organized by themes. The disclosed system can present the media item navigation graphical user interface without altering the original folder structure.

    Automatically generating theme-based folders by clustering media items in a semantic space
    3.
    发明授权
    Automatically generating theme-based folders by clustering media items in a semantic space 有权

    公开(公告)号：US11030257B2

    公开(公告)日：2021-06-08

    申请号：US16417232

    申请日：2019-05-20

    Applicant: Adobe Inc.

    Inventor： Jonas Dahl ,  Sudheer Tumu ,  Nithyanand Kota ,  Mihir Naware ,  Maneesh Dewan ,  Jatin Chhugani ,  Ganesh Satish Mallya

    IPC: G06F40/30 ,  G06F16/906 ,  G06K9/46 ,  G06N3/02 ,  G06F16/16

    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for clustering media items in a semantic space to generate theme-based folders that organize media items by content theme. In particular, the disclosed systems can access media items that are stored in an original folder structure. The disclosed systems can generate content-based tags for each media item in a collection of media items. Based on the generated tags, the disclosed systems can map the collection of media items to a semantic space and cluster the collection of media items. The disclosed systems determine themes for the clusters based on the generated tags. The disclosed systems can present a media item navigation graphical user interface comprising the collection of media items organized by themes. The disclosed system can present the media item navigation graphical user interface without altering the original folder structure.

    IDENTIFYING DIGITAL ATTRIBUTES FROM MULTIPLE ATTRIBUTE GROUPS WITHIN TARGET DIGITAL IMAGES UTILIZING A DEEP COGNITIVE ATTRIBUTION NEURAL NETWORK
    4.
    发明申请
    IDENTIFYING DIGITAL ATTRIBUTES FROM MULTIPLE ATTRIBUTE GROUPS WITHIN TARGET DIGITAL IMAGES UTILIZING A DEEP COGNITIVE ATTRIBUTION NEURAL NETWORK 有权

    公开(公告)号：US20210073267A1

    公开(公告)日：2021-03-11

    申请号：US16564831

    申请日：2019-09-09

    Applicant: Adobe, Inc.

    Inventor： Ayush Chopra ,  Mausoom Sarkar ,  Jonas Dahl ,  Hiresh Gupta ,  Balaji Krishnamurthy ,  Abhishek Sinha

    IPC: G06F16/535 ,  G06K9/62 ,  G06F16/55 ,  G06N3/04 ,  G06F17/15

    Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media for generating tags for an object portrayed in a digital image based on predicted attributes of the object. For example, the disclosed systems can utilize interleaved neural network layers of alternating inception layers and dilated convolution layers to generate a localization feature vector. Based on the localization feature vector, the disclosed systems can generate attribute localization feature embeddings, for example, using some pooling layer such as a global average pooling layer. The disclosed systems can then apply the attribute localization feature embeddings to corresponding attribute group classifiers to generate tags based on predicted attributes. In particular, attribute group classifiers can predict attributes as associated with a query image (e.g., based on a scoring comparison with other potential attributes of an attribute group). Based on the generated tags, the disclosed systems can respond to tag queries and search queries.

    Similarity propagation for one-shot and few-shot image segmentation
    6.
    发明授权
    Similarity propagation for one-shot and few-shot image segmentation 有权

    公开(公告)号：US11367271B2

    公开(公告)日：2022-06-21

    申请号：US16906954

    申请日：2020-06-19

    Applicant: ADOBE INC.

    Inventor： Mayur Hemani ,  Siddhartha Gairola ,  Ayush Chopra ,  Balaji Krishnamurthy ,  Jonas Dahl

    IPC: G06K9/62 ,  G06V10/46 ,  G06K9/46

    Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for one-shot and few-shot image segmentation on classes of objects that were not represented during training. In some embodiments, a dual prediction scheme may be applied in which query and support masks are jointly predicted using a shared decoder, which aids in similarity propagation between the query and support features. Additionally or alternatively, foreground and background attentive fusion may be applied to utilize cues from foreground and background feature similarities between the query and support images. Finally, to prevent overfitting on class-conditional similarities across training classes, input channel averaging may be applied for the query image during training. Accordingly, the techniques described herein may be used to achieve state-of-the-art performance for both one-shot and few-shot segmentation tasks.

    SIMILARITY PROPAGATION FOR ONE-SHOT AND FEW-SHOT IMAGE SEGMENTATION
    7.
    发明申请
    SIMILARITY PROPAGATION FOR ONE-SHOT AND FEW-SHOT IMAGE SEGMENTATION 有权

    公开(公告)号：US20210397876A1

    公开(公告)日：2021-12-23

    申请号：US16906954

    申请日：2020-06-19

    Applicant: ADOBE INC.

    Inventor： Mayur Hemani ,  Siddhartha Gairola ,  Ayush Chopra ,  Balaji Krishnamurthy ,  Jonas Dahl

    IPC: G06K9/46 ,  G06K9/62

    Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for one-shot and few-shot image segmentation on classes of objects that were not represented during training. In some embodiments, a dual prediction scheme may be applied in which query and support masks are jointly predicted using a shared decoder, which aids in similarity propagation between the query and support features. Additionally or alternatively, foreground and background attentive fusion may be applied to utilize cues from foreground and background feature similarities between the query and support images. Finally, to prevent overfitting on class-conditional similarities across training classes, input channel averaging may be applied for the query image during training. Accordingly, the techniques described herein may be used to achieve state-of-the-art performance for both one-shot and few-shot segmentation tasks.

    AUTOMATICALLY GENERATING THEME-BASED FOLDERS BY CLUSTERING MEDIA ITEMS IN A SEMANTIC SPACE
    8.
    发明申请
    AUTOMATICALLY GENERATING THEME-BASED FOLDERS BY CLUSTERING MEDIA ITEMS IN A SEMANTIC SPACE 审中-公开

    公开(公告)号：US20200372073A1

    公开(公告)日：2020-11-26

    申请号：US16417232

    申请日：2019-05-20

    Applicant: Adobe Inc.

    Inventor： Jonas Dahl ,  Sudheer Tumu ,  Nithyanand Kota ,  Mihir Naware ,  Maneesh Dewan ,  Jatin Chhugani ,  Ganesh Satish Mallya

    IPC: G06F16/906 ,  G06K9/46 ,  G06F16/16 ,  G06N3/02

    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for clustering media items in a semantic space to generate theme-based folders that organize media items by content theme. In particular, the disclosed systems can access media items that are stored in an original folder structure. The disclosed systems can generate content-based tags for each media item in a collection of media items. Based on the generated tags, the disclosed systems can map the collection of media items to a semantic space and cluster the collection of media items. The disclosed systems determine themes for the clusters based on the generated tags. The disclosed systems can present a media item navigation graphical user interface comprising the collection of media items organized by themes. The disclosed system can present the media item navigation graphical user interface without altering the original folder structure.

    Generating theme-based folders by clustering digital images in a semantic space
    10.
    发明授权
    Generating theme-based folders by clustering digital images in a semantic space 有权

    公开(公告)号：US11593438B2

    公开(公告)日：2023-02-28

    申请号：US17314651

    申请日：2021-05-07

    Applicant: Adobe Inc.

    Inventor： Jonas Dahl ,  Sudheer Tumu ,  Nithyanand Kota ,  Mihir Naware ,  Maneesh Dewan ,  Jatin Chhugani ,  Ganesh Satish Mallya

    IPC: G06F16/906 ,  G06N3/02 ,  G06F16/16 ,  G06V10/48

    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for clustering media items in a semantic space to generate theme-based folders that organize media items by content theme. In particular, the disclosed systems can access media items that are stored in an original folder structure. The disclosed systems can generate content-based tags for each media item in a collection of media items. Based on the generated tags, the disclosed systems can map the collection of media items to a semantic space and cluster the collection of media items. The disclosed systems determine themes for the clusters based on the generated tags. The disclosed systems can present a media item navigation graphical user interface comprising the collection of media items organized by themes. The disclosed system can present the media item navigation graphical user interface without altering the original folder structure.

Patent Agency Ranking