中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

75 records (took 0.014 seconds)

    Machine Learning Techniques for Generating Document Summaries Targeted to Affective Tone
    34.
    发明申请
    Machine Learning Techniques for Generating Document Summaries Targeted to Affective Tone 审中-公开

    公开(公告)号：US20200257757A1

    公开(公告)日：2020-08-13

    申请号：US16270191

    申请日：2019-02-07

    Applicant: Adobe Inc.

    Inventor： Kushal Chawla ,  Balaji Vasan Srinivasan ,  Niyati Himanshu Chhaya

    IPC: G06F17/24 ,  G06F17/27 ,  G06N20/00

    Abstract: An affective summarization system provides affective text summaries directed towards affective preferences of a user, such as psychological or linguistic preferences. The affective summarization system includes a summarization neural network and an affect predictor neural network. The affect predictor neural network is trained to provide a target affect level based on a word sequence, such as a word sequence for an article or other text document. The summarization neural network is trained to provide a summary sequence based on the target affect level and on the word sequence for the text document.

    Content to layout template mapping and transformation
    35.
    发明授权
    Content to layout template mapping and transformation 有权

    公开(公告)号：US10521494B2

    公开(公告)日：2019-12-31

    申请号：US15013809

    申请日：2016-02-02

    Applicant: Adobe Inc.

    Inventor： Balaji Vasan Srinivasan ,  Vineet Sharma ,  Varun Syal ,  Tanya Goyal ,  Shubhankar Suman Singh ,  Cedric Huesler

    IPC: G06F17/00 ,  G06F17/21 ,  G06F17/22 ,  G06F17/24 ,  G06F16/957

    Abstract: Content can be displayed in different manners on different devices (e.g., having different display sizes) using different layout templates. The techniques discussed herein automatically select a layout template for the content for a particular display device, and transform the content to that layout template for display. Generally, the content is categorized into multiple different categories, and the layout template is also categorized into the same categories. For each of the categories, a mapping of part of the content to a layout element of the layout template is selected. A content display for the layout template is generated by porting (and possibly transforming) the parts of the content into the mapped-to element (as indicated by the selected edges) of the layout. In one or more embodiments, the content display can then be displayed or communicated to another device for display.

    TEXT-CONDITIONED VISUAL ATTENTION FOR MULTIMODAL MACHINE LEARNING MODELS
    36.
    发明申请
    TEXT-CONDITIONED VISUAL ATTENTION FOR MULTIMODAL MACHINE LEARNING MODELS 有权

    公开(公告)号：US20250022263A1

    公开(公告)日：2025-01-16

    申请号：US18351211

    申请日：2023-07-12

    Applicant: Adobe Inc.

    Inventor： Prateksha Udhayanan ,  Srikrishna Karanam ,  Balaji Vasan Srinivasan

    IPC: G06V10/80 ,  G06T11/60 ,  G06V10/82

    Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for conditioning images on modification texts to generate multi-modal gradient attention maps. In particular, in some embodiments, the disclosed systems generate, utilizing a vision-language neural network of an image-text comparison machine learning model, a reference text-image feature vector based on a reference image and a modification text. Additionally, in some embodiments, the disclosed systems generate, utilizing the vision-language neural network of the image-text comparison machine learning model, a target text-image feature vector based on a target image and the modification text. Moreover, in some implementations, the disclosed systems generate, from the reference text-image feature vector and the target text-image feature vector, a multi-modal gradient attention map reflecting a visual grounding of the image-text comparison machine learning model relative to the modification text.

    Cross view template recommendation system
    37.
    发明授权
    Cross view template recommendation system 有权

    公开(公告)号：US12013883B1

    公开(公告)日：2024-06-18

    申请号：US18200856

    申请日：2023-05-23

    Applicant: Adobe Inc.

    Inventor： Tripti Shukla ,  Vishwa Vinay ,  Srikrishna Karanam ,  Praneetha Vaddamanu ,  Balaji Vasan Srinivasan

    IPC: G06F3/0484 ,  G06F16/31 ,  G06F16/332 ,  G06F40/106 ,  G06F40/109 ,  G06F40/186

    CPC classification number: G06F16/3323 ,  G06F16/31 ,  G06F40/106 ,  G06F40/109 ,  G06F40/186

    Abstract: An illustrator system determines, for each feature of a set of features, a feature representation for an electronic document displayed via a user interface, based on a plurality of elements of the electronic document. The system receives a selection from among the set of features of (1) a query feature and of (2) a target feature and determines, for each replacement template of a set of replacement templates, a compatibility score based on the feature representation for the electronic document determined for the query feature and a target feature representation of the replacement template determined for the target feature, the representations being determined in a joint representation space. The system selects one or more replacement electronic documents based on the determined compatibility scores. The system displays a preview for each replacement electronic document and displays a particular replacement electronic document responsive to receiving a selection of a preview.

Patent Agency Ranking