中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

6 records (took 0.017 seconds)

    ACCURATE TAG RELEVANCE PREDICTION FOR IMAGE SEARCH
    1.
    发明申请
    ACCURATE TAG RELEVANCE PREDICTION FOR IMAGE SEARCH 审中-公开

    公开(公告)号：US20200250465A1

    公开(公告)日：2020-08-06

    申请号：US16853111

    申请日：2020-04-20

    Applicant: Adobe Inc.

    Inventor： ZHE LIN ,  XIAOHUI SHEN ,  JONATHAN BRANDT ,  JIANMING ZHANG ,  CHEN FANG

    IPC: G06K9/62 ,  G06F16/51 ,  G06F16/28 ,  G06F16/2457 ,  G06K9/46 ,  G06F16/583 ,  G06N3/04 ,  G06N3/08

    Abstract: Embodiments of the present invention provide an automated image tagging system that can predict a set of tags, along with relevance scores, that can be used for keyword-based image retrieval, image tag proposal, and image tag auto-completion based on user input. Initially, during training, a clustering technique is utilized to reduce cluster imbalance in the data that is input into a convolutional neural network (CNN) for training feature data. In embodiments, the clustering technique can also be utilized to compute data point similarity that can be utilized for tag propagation (to tag untagged images). During testing, a diversity based voting framework is utilized to overcome user tagging biases. In some embodiments, bigram re-weighting can down-weight a keyword that is likely to be part of a bigram based on a predicted tag set.

    CUSTOMIZABLE IMAGE CROPPING USING BODY KEY POINTS
    2.
    发明申请
    CUSTOMIZABLE IMAGE CROPPING USING BODY KEY POINTS 审中-公开

    公开(公告)号：US20190304064A1

    公开(公告)日：2019-10-03

    申请号：US15940452

    申请日：2018-03-29

    Applicant: ADOBE INC.

    Inventor： JIANMING ZHANG

    IPC: G06T3/40 ,  G06K9/00 ,  G06K9/32

    Abstract: Systems, methods and computer storage media for using body key points in received images and cropping rule representations to crop images are provided. Cropping configurations are received that specify characteristics of cropped images. Also obtained are images to crop. For a given image, a plurality of body key points is determined. A list of tuples is determined from the body key points and the cropping configurations. Each tuple includes a reference point, a reference length and an offset scale. A possible anchor level is calculated for each tuple. Each tuple sharing a common reference body key point is aggregated and a border representation is determined by calculating the minimum, maximum or average of all such possible anchor levels. The image is then cropped at the border representation. This process can be repeated for multiple border representations within a single image and/or for multiple images.

    ROBUST TRAINING OF LARGE-SCALE OBJECT DETECTORS WITH A NOISY DATASET
    3.
    发明申请
    ROBUST TRAINING OF LARGE-SCALE OBJECT DETECTORS WITH A NOISY DATASET 审中-公开

    公开(公告)号：US20200334501A1

    公开(公告)日：2020-10-22

    申请号：US16388115

    申请日：2019-04-18

    Applicant: ADOBE INC

    Inventor： ZHE LIN ,  MINGYANG LING ,  JIANMING ZHANG ,  JASON KUEN ,  FEDERICO PERAZZI ,  BRETT BUTTERFIELD ,  BALDO FAIETA

    IPC: G06K9/62 ,  G06N3/08 ,  G06K9/34

    Abstract: Systems and methods are described for object detection within a digital image using a hierarchical softmax function. The method may include applying a first softmax function of a softmax hierarchy on a digital image based on a first set of object classes that are children of a root node of a class hierarchy, then apply a second (and subsequent) softmax functions to the digital image based on a second (and subsequent) set of object classes, where the second (and subsequent) object classes are children nodes of an object class from the first (or parent) object classes. The methods may then include generating an object recognition output using a convolutional neural network (CNN) based at least in part on applying the first and second (and subsequent) softmax functions. In some cases, the hierarchical softmax function is the loss function for the CNN.

    NEURAL NETWORKS FOR CROPPING IMAGES BASED ON BODY KEY POINTS
    4.
    发明申请
    NEURAL NETWORKS FOR CROPPING IMAGES BASED ON BODY KEY POINTS 审中-公开

    公开(公告)号：US20200320668A1

    公开(公告)日：2020-10-08

    申请号：US16906990

    申请日：2020-06-19

    Applicant: ADOBE INC.

    Inventor： JIANMING ZHANG

    IPC: G06T3/40 ,  G06K9/32 ,  G06K9/00

    Abstract: Systems, methods and computer storage media for using body key points in received images and cropping rule representations to crop images are provided. Cropping configurations are received that specify characteristics of cropped images. Also obtained are images to crop. For a given image, a plurality of body key points is determined. A list of tuples is determined from the body key points and the cropping configurations. Each tuple includes a reference point, a reference length and an offset scale. A possible anchor level is calculated for each tuple. Each tuple sharing a common reference body key point is aggregated and a border representation is determined by calculating the minimum, maximum or average of all such possible anchor levels. The image is then cropped at the border representation. This process can be repeated for multiple border representations within a single image and/or for multiple images.

Patent Agency Ranking