Scene-to-text conversion
    1.
    发明授权

    公开(公告)号:US12033381B2

    公开(公告)日:2024-07-09

    申请号:US17466379

    申请日:2021-09-03

    Applicant: Apple Inc.

    Inventor: Jack Greasley

    Abstract: Various implementations disclosed herein include devices, systems, and methods for performing scene-to-text conversion. In various implementations, a device includes a non-transitory memory and one or more processors coupled with the non-transitory memory. In some implementations, a method includes obtaining environmental data corresponding to an environment. Based on the environmental data, a plurality of objects that are in the environment are identified. An audio output describing at least a first object of the plurality of objects in the environment is generated based on a characteristic value associated with a user of the device. The audio output is outputted.

    Scene-to-Text Conversion
    2.
    发明申请

    公开(公告)号:US20210397842A1

    公开(公告)日:2021-12-23

    申请号:US17466379

    申请日:2021-09-03

    Applicant: Apple Inc.

    Inventor: Jack Greasley

    Abstract: Various implementations disclosed herein include devices, systems, and methods for performing scene-to-text conversion. In various implementations, a device includes a non-transitory memory and one or more processors coupled with the non-transitory memory. In some implementations, a method includes obtaining environmental data corresponding to an environment. Based on the environmental data, a plurality of objects that are in the environment are identified. An audio output describing at least a first object of the plurality of objects in the environment is generated based on a characteristic value associated with a user of the device. The audio output is outputted.

    Content Generation Based on Audience Engagement

    公开(公告)号:US20210400342A1

    公开(公告)日:2021-12-23

    申请号:US17463097

    申请日:2021-08-31

    Applicant: Apple Inc.

    Abstract: Various implementations disclosed herein include devices, systems, and methods for performing content generation based on audience engagement. In some implementations, a method includes presenting a first portion of content. Engagement data is obtained for an audience comprising a plurality of persons while the first portion of the content is presented. Based on the engagement data, a collective engagement level of the audience is determined for the first portion of the content. A second portion of the content that has not been presented is adjusted based on the collective engagement level of the audience for the first portion of the content in order to satisfy an engagement threshold. After adjusting the second portion of the content, the second portion of the content is presented to the audience.

    Content generation based on audience engagement

    公开(公告)号:US11949949B2

    公开(公告)日:2024-04-02

    申请号:US17463097

    申请日:2021-08-31

    Applicant: Apple Inc.

    CPC classification number: H04N21/44218 G06F3/013 G06V40/176 H04N13/117

    Abstract: Various implementations disclosed herein include devices, systems, and methods for performing content generation based on audience engagement. In some implementations, a method includes presenting a first portion of content. Engagement data is obtained for an audience comprising a plurality of persons while the first portion of the content is presented. Based on the engagement data, a collective engagement level of the audience is determined for the first portion of the content. A second portion of the content that has not been presented is adjusted based on the collective engagement level of the audience for the first portion of the content in order to satisfy an engagement threshold. After adjusting the second portion of the content, the second portion of the content is presented to the audience.

    PER-PIXEL FILTER
    6.
    发明申请

    公开(公告)号:US20220188989A1

    公开(公告)日:2022-06-16

    申请号:US17686059

    申请日:2022-03-03

    Applicant: Apple Inc.

    Inventor: Jack Greasley

    Abstract: Various implementations disclosed herein include devices, systems, and methods for per-pixel filtering. In some implementations, a method includes obtaining an image data frame. In some implementations, the image data frame includes a plurality of pixels. In some implementations, the method includes generating a respective pixel characterization vector for each of the plurality of pixels. In some implementations, each pixel characterization vector includes an object label indicating an object type that the corresponding pixel of the plurality of pixels represents. In some implementations, the method includes modifying corresponding pixel data of the plurality of pixels having a first object label. In some implementations, the method includes synthesizing a first modified image data frame that includes modified pixel data for the plurality of pixels having the first object label and unmodified pixel data for the plurality of pixels not having the first object label.

    Per-pixel filter
    7.
    发明授权

    公开(公告)号:US12236560B2

    公开(公告)日:2025-02-25

    申请号:US17686059

    申请日:2022-03-03

    Applicant: Apple Inc.

    Inventor: Jack Greasley

    Abstract: Various implementations disclosed herein include devices, systems, and methods for per-pixel filtering. In some implementations, a method includes obtaining an image data frame. In some implementations, the image data frame includes a plurality of pixels. In some implementations, the method includes generating a respective pixel characterization vector for each of the plurality of pixels. In some implementations, each pixel characterization vector includes an object label indicating an object type that the corresponding pixel of the plurality of pixels represents. In some implementations, the method includes modifying corresponding pixel data of the plurality of pixels having a first object label. In some implementations, the method includes synthesizing a first modified image data frame that includes modified pixel data for the plurality of pixels having the first object label and unmodified pixel data for the plurality of pixels not having the first object label.

    Per-pixel filter
    8.
    发明授权

    公开(公告)号:US11301966B2

    公开(公告)日:2022-04-12

    申请号:US16676245

    申请日:2019-11-06

    Applicant: Apple Inc.

    Inventor: Jack Greasley

    Abstract: Various implementations disclosed herein include devices, systems, and methods for per-pixel filtering. In some implementations, a method includes obtaining an image data frame. In some implementations, the image data frame includes a plurality of pixels. In some implementations, the method includes generating a respective pixel characterization vector for each of the plurality of pixels. In some implementations, each pixel characterization vector includes an object label indicating an object type that the corresponding pixel of the plurality of pixels represents. In some implementations, the method includes modifying corresponding pixel data of the plurality of pixels having a first object label. In some implementations, the method includes synthesizing a first modified image data frame that includes modified pixel data for the plurality of pixels having the first object label and unmodified pixel data for the plurality of pixels not having the first object label.

    CONFIGURING OBJECTIVE-EFFECTUATORS FOR SYNTHESIZED REALITY SETTINGS

    公开(公告)号:US20210042022A1

    公开(公告)日:2021-02-11

    申请号:US16959333

    申请日:2019-01-18

    Applicant: Apple Inc.

    Abstract: In some implementations, a method includes obtaining a set of preselected attribute values for an objective-effectuator. In some implementations, the method includes while displaying a user interface including a plurality of configuration control affordances provided to effect configuration of one or more attributes characterizing the objective-effectuator, in response to receiving an input indicative of manipulation of a first configuration control affordance, setting a corresponding first attribute to a particular preselected attribute value, and modifying display of the plurality of configuration control affordances in order to change the number of the plurality of configuration control affordances displayed. In some implementations, the method includes configuring the objective-effectuator at least based on the particular preselected attribute value of the first attribute. In some implementations, the objective-effectuator is associated with a set of predefined actions.

    PER-PIXEL FILTER
    10.
    发明申请
    PER-PIXEL FILTER 审中-公开

    公开(公告)号:US20200184608A1

    公开(公告)日:2020-06-11

    申请号:US16676245

    申请日:2019-11-06

    Applicant: Apple Inc.

    Inventor: Jack Greasley

    Abstract: Various implementations disclosed herein include devices, systems, and methods for per-pixel filtering. In some implementations, a method includes obtaining an image data frame. In some implementations, the image data frame includes a plurality of pixels. In some implementations, the method includes generating a respective pixel characterization vector for each of the plurality of pixels. In some implementations, each pixel characterization vector includes an object label indicating an object type that the corresponding pixel of the plurality of pixels represents. In some implementations, the method includes modifying corresponding pixel data of the plurality of pixels having a first object label. In some implementations, the method includes synthesizing a first modified image data frame that includes modified pixel data for the plurality of pixels having the first object label and unmodified pixel data for the plurality of pixels not having the first object label.

Patent Agency Ranking