中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

197 records (took 0.032 seconds)

    Shortlist computation for searching high-dimensional spaces
    131.
    发明授权
    Shortlist computation for searching high-dimensional spaces 有权

    公开(公告)号：US09940100B2

    公开(公告)日：2018-04-10

    申请号：US14473104

    申请日：2014-08-29

    Applicant: Adobe Systems Incorporated

    Inventor： Zhe Lin ,  Jonathan Brandt ,  Xiaohui Shen ,  Jae-Pil Heo

    IPC: G06F17/30 ,  G06F7/24

    CPC classification number: G06F7/24 ,  G06F17/30268 ,  G06F17/30271 ,  G06F17/30622

    Abstract: Techniques are disclosed for indexing and searching high-dimensional data using inverted file structures and product quantization encoding. An image descriptor is quantized using a form of product quantization to determine which of several inverted lists the image descriptor is to be stored. The image descriptor is appended to the corresponding inverted list with a compact coding using a product quantization encoding scheme. When processing a query, a shortlist is computed that includes a set of candidate search results. The shortlist is based on the orthogonality between two random vectors in high-dimensional spaces. The inverted lists are traversed in the order of the distance between the query and the centroid of a coarse quantizer corresponding to each inverted list. The shortlist is ranked according to the distance estimated by a form of product quantization, and the top images referred to by the ranked shortlist are reported as the search results.

    SEMANTIC CLASS LOCALIZATION IN IMAGES
    132.
    发明申请
    SEMANTIC CLASS LOCALIZATION IN IMAGES 有权

    公开(公告)号：US20170344884A1

    公开(公告)日：2017-11-30

    申请号：US15164310

    申请日：2016-05-25

    Applicant: Adobe Systems Incorporated

    Inventor： Zhe Lin ,  Xiaohui Shen ,  Jonathan W. Brandt ,  Jianming Zhang

    IPC: G06N3/08 ,  G06F17/30

    CPC classification number: G06N3/084 ,  G06F17/30259

    Abstract: Semantic class localization techniques and systems are described. In one or more implementation, a technique is employed to back communicate relevancies of aggregations back through layers of a neural network. Through use of these relevancies, activation relevancy maps are created that describe relevancy of portions of the image to the classification of the image as corresponding to a semantic class. In this way, the semantic class is localized to portions of the image. This may be performed through communication of positive and not negative relevancies, use of contrastive attention maps to different between semantic classes and even within a same semantic class through use of a self-contrastive technique.

    Object detection using cascaded convolutional neural networks
    136.
    发明授权
    Object detection using cascaded convolutional neural networks 有权

    公开(公告)号：US09697416B2

    公开(公告)日：2017-07-04

    申请号：US15196478

    申请日：2016-06-29

    Applicant: Adobe Systems Incorporated

    Inventor： Xiaohui Shen ,  Haoxiang Li ,  Zhe Lin ,  Jonathan W. Brandt

    IPC: G06K9/62 ,  G06K9/00 ,  G06K9/46

    CPC classification number: G06K9/00288 ,  G06K9/4628 ,  G06K9/6257 ,  G06N3/0454

    Abstract: Different candidate windows in an image are identified, such as by sliding a rectangular or other geometric shape of different sizes over an image to identify portions of the image (groups of pixels in the image). The candidate windows are analyzed by a set of convolutional neural networks, which are cascaded so that the input of one convolutional neural network layer is based on the input of another convolutional neural network layer. Each convolutional neural network layer drops or rejects one or more candidate windows that the convolutional neural network layer determines does not include an object (e.g., a face). The candidate windows that are identified as including an object (e.g., a face) are analyzed by another one of the convolutional neural network layers. The candidate windows identified by the last of the convolutional neural network layers are the indications of the objects (e.g., faces) in the image.

    Image Cropping Suggestion Using Multiple Saliency Maps
    137.
    发明申请
    Image Cropping Suggestion Using Multiple Saliency Maps 审中-公开

    公开(公告)号：US20170178291A1

    公开(公告)日：2017-06-22

    申请号：US15448138

    申请日：2017-03-02

    Applicant: Adobe Systems Incorporated

    Inventor： Zhe Lin ,  Radomir Mech ,  Xiaohui Shen ,  Brian L. Price ,  Jianming Zhang ,  Anant Gilra ,  Jen-Chan Jeff Chien

    IPC: G06T3/40 ,  G06K9/46 ,  G06T11/60 ,  G06T3/00

    CPC classification number: G06T3/40 ,  G06K9/4671 ,  G06T3/0012 ,  G06T11/60 ,  G06T2210/22

    Abstract: Image cropping suggestion using multiple saliency maps is described. In one or more implementations, component scores, indicative of visual characteristics established for visually-pleasing croppings, are computed for candidate image croppings using multiple different saliency maps. The visual characteristics on which a candidate image cropping is scored may be indicative of its composition quality, an extent to which it preserves content appearing in the scene, and a simplicity of its boundary. Based on the component scores, the croppings may be ranked with regard to each of the visual characteristics. The rankings may be used to cluster the candidate croppings into groups of similar croppings, such that croppings in a group are different by less than a threshold amount and croppings in different groups are different by at least the threshold amount. Based on the clustering, croppings may then be chosen, e.g., to present them to a user for selection.

    Image tagging
    140.
    发明授权
    Image tagging 有权

    公开(公告)号：US09607014B2

    公开(公告)日：2017-03-28

    申请号：US14068238

    申请日：2013-10-31

    Applicant: Adobe Systems Incorporated

    Inventor： Zhaowen Wang ,  Jianchao Yang ,  Zhe Lin ,  Jonathan Brandt

    IPC: G06F17/30 ,  G06K9/62

    CPC classification number: G06F17/30265 ,  G06K9/6263 ,  G06K2209/27

    Abstract: A system is configured to annotate an image with tags. As configured, the system accesses an image and generates a set of vectors for the image. The set of vectors may be generated by mathematically transforming the image, such as by applying a mathematical transform to predetermined regions of the image. The system may then query a database of tagged images by submitting the set of vectors as search criteria to a search engine. The querying of the database may obtain a set of tagged images. Next, the system may rank the obtained set of tagged images according to similarity scores that quantify degrees of similarity between the image and each tagged image obtained. Tags from a top-ranked subset of the tagged images may be extracted by the system, which may then annotate the image with these extracted tags.

Patent Agency Ranking