System and method for photo scene searching

    公开(公告)号:US11442980B2

    公开(公告)日:2022-09-13

    申请号:US16222241

    申请日:2018-12-17

    Applicant: Oath Inc.

    Inventor: JenHao Hsiao

    Abstract: Users may have a variety of photos, but lack a mechanism to organize the photos. For example, a user may desire to access a photo of a child in front of a national monument, but may be unable to locate the photo amongst the photos. Accordingly, a photo query may be generated utilizing a photo query interface populated with a face query attribute (e.g., a proxy icon, a photo of a face, etc.), a face position attribute (e.g., a position of the face query attribute), and/or a location query attribute (e.g., a background of a photo, such as a forest, a monument, etc.) using drag and drop functionality and/or any other query construction functionality. One or more photos having attributes corresponding to the photo query may be identified and provided to the user.

    Image searching
    2.
    发明授权

    公开(公告)号:US10719763B2

    公开(公告)日:2020-07-21

    申请号:US16392305

    申请日:2019-04-23

    Applicant: Oath Inc.

    Inventor: JenHao Hsiao

    Abstract: As provided herein, a domain model, corresponding to a domain of an image, may be merged with a pre-trained fundamental model to generate a trained fundamental model. The trained fundamental model may comprise a feature description of the image converted into a binary code. Responsive to a user submitting a search query, a coarse image search may be performed, using a search query binary code derived from the search query, to identify a candidate group, comprising one or more images, having binary codes corresponding to the search query binary code. A fine image search may be performed on the candidate group utilizing a search query feature description derived from the search query. The fine image search may be used to rank images within the candidate group based upon a similarity between the search query feature description and feature descriptions of the one or more images within the candidate group.

    IMAGE SEARCHING
    3.
    发明申请
    IMAGE SEARCHING 审中-公开

    公开(公告)号:US20180225573A1

    公开(公告)日:2018-08-09

    申请号:US15948061

    申请日:2018-04-09

    Applicant: Oath Inc.

    Inventor: JenHao Hsiao

    Abstract: As provided herein, a domain model, corresponding to a domain of an image, may be merged with a pre-trained fundamental model to generate a trained fundamental model. The trained fundamental model may comprise a feature description of the image converted into a binary code. Responsive to a user submitting a search query, a coarse image search may be performed, using a search query binary code derived from the search query, to identify a candidate group, comprising one or more images, having binary codes corresponding to the search query binary code. A fine image search may be performed on the candidate group utilizing a search query feature description derived from the search query. The fine image search may be used to rank images within the candidate group based upon a similarity between the search query feature description and feature descriptions of the one or more images within the candidate group.

    On-line product related recommendations

    公开(公告)号:US11151630B2

    公开(公告)日:2021-10-19

    申请号:US14325192

    申请日:2014-07-07

    Applicant: Oath Inc.

    Inventor: JenHao Hsiao Jia Li

    Abstract: Example methods, apparatuses, and/or articles of manufacture are disclosed that may be implemented, in whole or in part, using one or more computing devices to facilitate or support one or more processes and/or operations for one or more on-line recommendations, such as product-related recommendations, for example.

    IMAGE SEARCHING
    5.
    发明申请
    IMAGE SEARCHING 审中-公开

    公开(公告)号:US20200349436A1

    公开(公告)日:2020-11-05

    申请号:US16935069

    申请日:2020-07-21

    Applicant: Oath Inc.

    Inventor: JenHao Hsiao

    Abstract: As provided herein, a domain model, corresponding to a domain of an image, may be merged with a pre-trained fundamental model to generate a trained fundamental model. The trained fundamental model may comprise a feature description of the image converted into a binary code. Responsive to a user submitting a search query, a coarse image search may be performed, using a search query binary code derived from the search query, to identify a candidate group, comprising one or more images, having binary codes corresponding to the search query binary code. A fine image search may be performed on the candidate group utilizing a search query feature description derived from the search query. The fine image search may be used to rank images within the candidate group based upon a similarity between the search query feature description and feature descriptions of the one or more images within the candidate group.

    IMAGE SEARCHING
    6.
    发明申请
    IMAGE SEARCHING 审中-公开

    公开(公告)号:US20190251438A1

    公开(公告)日:2019-08-15

    申请号:US16392305

    申请日:2019-04-23

    Applicant: Oath Inc.

    Inventor: JenHao Hsiao

    Abstract: As provided herein, a domain model, corresponding to a domain of an image, may be merged with a pre-trained fundamental model to generate a trained fundamental model. The trained fundamental model may comprise a feature description of the image converted into a binary code. Responsive to a user submitting a search query, a coarse image search may be performed, using a search query binary code derived from the search query, to identify a candidate group, comprising one or more images, having binary codes corresponding to the search query binary code. A fine image search may be performed on the candidate group utilizing a search query feature description derived from the search query. The fine image search may be used to rank images within the candidate group based upon a similarity between the search query feature description and feature descriptions of the one or more images within the candidate group.

    SYSTEM AND METHOD FOR PHOTO SCENE SEARCHING
    7.
    发明申请

    公开(公告)号:US20190121821A1

    公开(公告)日:2019-04-25

    申请号:US16222241

    申请日:2018-12-17

    Applicant: Oath Inc.

    Inventor: JenHao Hsiao

    Abstract: Users may have a variety of photos, but lack a mechanism to organize the photos. For example, a user may desire to access a photo of a child in front of a national monument, but may be unable to locate the photo amongst the photos. Accordingly, a photo query may be generated utilizing a photo query interface populated with a face query attribute (e.g., a proxy icon, a photo of a face, etc.), a face position attribute (e.g., a position of the face query attribute), and/or a location query attribute (e.g., a background of a photo, such as a forest, a monument, etc.) using drag and drop functionality and/or any other query construction functionality. One or more photos having attributes corresponding to the photo query may be identified and provided to the user.

    Image searching
    8.
    发明授权

    公开(公告)号:US10268952B2

    公开(公告)日:2019-04-23

    申请号:US15948061

    申请日:2018-04-09

    Applicant: Oath Inc.

    Inventor: JenHao Hsiao

    Abstract: As provided herein, a domain model, corresponding to a domain of an image, may be merged with a pre-trained fundamental model to generate a trained fundamental model. The trained fundamental model may comprise a feature description of the image converted into a binary code. Responsive to a user submitting a search query, a coarse image search may be performed, using a search query binary code derived from the search query, to identify a candidate group, comprising one or more images, having binary codes corresponding to the search query binary code. A fine image search may be performed on the candidate group utilizing a search query feature description derived from the search query. The fine image search may be used to rank images within the candidate group based upon a similarity between the search query feature description and feature descriptions of the one or more images within the candidate group.

    System and method for photo scene searching

    公开(公告)号:US10157192B2

    公开(公告)日:2018-12-18

    申请号:US14664011

    申请日:2015-03-20

    Applicant: Oath Inc.

    Inventor: JenHao Hsiao

    Abstract: Users may have a variety of photos, but lack a mechanism to organize the photos. For example, a user may desire to access a photo of a child in front of a national monument, but may be unable to locate the photo amongst the photos. Accordingly, a photo query may be generated utilizing a photo query interface populated with a face query attribute (e.g., a proxy icon, a photo of a face, etc.), a face position attribute (e.g., a position of the face query attribute), and/or a location query attribute (e.g., a background of a photo, such as a forest, a monument, etc.) using drag and drop functionality and/or any other query construction functionality. One or more photos having attributes corresponding to the photo query may be identified and provided to the user.

Patent Agency Ranking