利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

590 条记录 (耗时 0.027 秒)

    AUTOMATED VIDEO GENERATION FROM IMAGES FOR E-COMMERCE APPLICATIONS
    3.
    发明公开
    AUTOMATED VIDEO GENERATION FROM IMAGES FOR E-COMMERCE APPLICATIONS 审中-实审

    公开(公告)号：EP4398175A3

    公开(公告)日：2024-08-07

    申请号：EP24175068.6

    申请日：2022-12-06

    申请人： eBay Inc.

    发明人： SOLMAZ, Berkan

    IPC分类号： G06Q30/0601 ,  G06Q30/0241

    CPC分类号： G06Q30/0643 ,  G06Q30/0276

    摘要： Systems and methods are provided for automatically generating a video associated with an item in the marketplace. An image receiver receives images associated with an item of an item listing. An image extractor generates visual descriptors for each image through computer vision analysis and extracts a unique set of images by removing redundant images. An image sorter sorts images in the unique set of images based on an item category and generates a sequence of images for generating a video. A text placer automatically identifies a region in an image and inserts text into the image using textual attributes as predicted by a model. A video data optimizes a generated video using another model trained based on manual adjustments previously made to other exemplary video data. The disclosed technology publishes the automatically generated video data for viewing by viewers in the marketplace.

    CONCEPT REFINEMENT USING CONCEPT ACTIVATION VECTORS
    5.
    发明公开
    CONCEPT REFINEMENT USING CONCEPT ACTIVATION VECTORS 审中-实审

    公开(公告)号：EP4361849A1

    公开(公告)日：2024-05-01

    申请号：EP23206122.6

    申请日：2023-10-26

    申请人： eBay Inc.

    发明人： BASIN, Dmitry ,  BEN-SHAUL, Ido

    IPC分类号： G06F16/9532

    CPC分类号： G06F16/9532

    摘要： A search query and a concept comprising a feature are received from a user. Positive and negative item sets are identified, where items of the positive item set comprise the feature and items of the negative item set do not comprise the feature. A hyperplane located between the positive and negative item sets is generated using a machine learning model. A concept activation vector (CAV) orthogonal to the hyperplane is determined. The CAV is used to produce a modified search query vector. Based on comparing the modified search query vector with item vectors, a second set of search results is provided.