知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

319 records (took 0.031 seconds)

    VIDEO DEPTH ESTIMATION BASED ON TEMPORAL ATTENTION
    2.
    发明公开
    VIDEO DEPTH ESTIMATION BASED ON TEMPORAL ATTENTION 审中-公开

    公开(公告)号：US20240346673A1

    公开(公告)日：2024-10-17

    申请号：US18676414

    申请日：2024-05-28

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Haoyu Ren ,  Mostafa El-Khamy ,  Jungwon Lee

    IPC: G06T7/579 ,  G06T3/18 ,  G06T7/194

    CPC classification number: G06T7/579 ,  G06T7/194 ,  G06T3/18 ,  G06T2207/10016 ,  G06T2207/20021 ,  G06T2207/20084

    Abstract: A method of depth detection based on a plurality of video frames includes receiving a plurality of input frames including a first input frame, a second input frame, and a third input frame respectively corresponding to different capture times, convolving the first to third input frames to generate a first feature map, a second feature map, and a third feature map corresponding to the different capture times, calculating a temporal attention map based on the first to third feature maps, the temporal attention map including a plurality of weights corresponding to different pairs of feature maps from among the first to third feature maps, each weight of the plurality of weights indicating a similarity level of a corresponding pair of feature maps, and applying the temporal attention map to the first to third feature maps to generate a feature map with temporal attention.

    Video depth estimation based on temporal attention
    4.
    发明授权
    Video depth estimation based on temporal attention 有权

    公开(公告)号：US11995856B2

    公开(公告)日：2024-05-28

    申请号：US18080599

    申请日：2022-12-13

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Haoyu Ren ,  Mostafa El Khamy ,  Jungwon Lee

    IPC: G06T7/579 ,  G06T3/18 ,  G06T7/194

    CPC classification number: G06T7/579 ,  G06T7/194 ,  G06T3/18 ,  G06T2207/10016 ,  G06T2207/20021 ,  G06T2207/20084

    Abstract: A method of depth detection based on a plurality of video frames includes receiving a plurality of input frames including a first input frame, a second input frame, and a third input frame respectively corresponding to different capture times, convolving the first to third input frames to generate a first feature map, a second feature map, and a third feature map corresponding to the different capture times, calculating a temporal attention map based on the first to third feature maps, the temporal attention map including a plurality of weights corresponding to different pairs of feature maps from among the first to third feature maps, each weight of the plurality of weights indicating a similarity level of a corresponding pair of feature maps, and applying the temporal attention map to the first to third feature maps to generate a feature map with temporal attention.

    Electronic device comprising expandable display, and method for providing content of electronic device
    5.
    发明授权
    Electronic device comprising expandable display, and method for providing content of electronic device 有权

    公开(公告)号：US11907494B2

    公开(公告)日：2024-02-20

    申请号：US18308289

    申请日：2023-04-27

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Juyeoung Kim ,  Joseph Kim ,  Jungwon Lee

    IPC: G06F3/0481 ,  H04M1/02 ,  G06F1/16 ,  G06F3/14

    CPC classification number: G06F3/0481 ,  G06F1/1624 ,  H04M1/0235 ,  G06F3/1431 ,  G06F2203/04803

    Abstract: An electronic device is provided. The electronic device includes a display including a main display area and at least one expansion display area expandable from the main display area, a communication module, and a processor, wherein the processor is configured to execute an application of the electronic device in a first state in which the display is not expanded or in a second state in which the display is expanded, display first content on the display, establish a connection with an external device, receive a context generated from the external device, when the context is received, determine a position to display second content related to the context, from among the main display area or the at least one expansion display area, based on a type of the first content and whether the display is in the first state or the second state, and display the second content at the determined position.

    Method for detecting black bar included in video content, and electronic device therefor
    7.
    发明授权
    Method for detecting black bar included in video content, and electronic device therefor 有权

    公开(公告)号：US11843826B2

    公开(公告)日：2023-12-12

    申请号：US16979939

    申请日：2019-03-13

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Seungjin Yu ,  Hansang Kim ,  Sungryul Bae ,  Jungwon Lee ,  Chaejung Lim

    IPC: H04N21/4402 ,  H04N21/44 ,  H04N21/472 ,  H04N21/485

    CPC classification number: H04N21/440272 ,  H04N21/44008 ,  H04N21/47205 ,  H04N21/4858

    Abstract: Various embodiments of the present invention relate to a device and a method for detecting a black bar in video content in an electronic device. An electronic device comprises a display device, a processor, and a memory automatically connected with the processor, wherein the memory, when executed, can store instructions for allowing the processor to: play video content on the basis of a request relating to the playing of the video content; acquire, on the basis of the request relating to the playing of the video content, time information relating to the detection period of a black bar included in the video content; detect, on the basis of the time information, the black bar by using at least one image frame of the video content included in the detection period, when the detection period arrives while the video content is played; and adjust, on the basis of the black bar included in the video content and the resolution of the display device, the size of an image area of the video content being played. Other embodiments are also possible.

Patent Agency Ranking