公开(公告)号：US20240320264A1

公开(公告)日：2024-09-26

申请号：US18123644

申请日：2023-03-20

Applicant: Disney Enterprises, Inc.

Inventor： Michael A. Radford ,  Pierre-Anthony Stivell Lemieux ,  Anil Chakrahari ,  Christian Parker ,  Mitchel C. Jacobs ,  Michael Fernandez ,  Larry Barker ,  Benjamin Eric Pearson

IPC: G06F16/732 ,  G06F16/74 ,  H04N21/262

CPC classification number: G06F16/7328 ,  G06F16/743 ,  H04N21/26258

Abstract: A differential media uploading system includes a hardware processor and a memory storing software code. The hardware processor executes the software code to receive a timeline file including a playlist track for a video file, and determine whether any pre-existing video frames stored in a media mastering system include a respective image depicted by a video frame contained in the video file. When it is determined that any of the pre-existing video frames include the respective image, the hardware processor executes the software code to disregard the video frame. When it is determined that none of the pre-existing video frames include the respective image, the hardware processor executes the software code to encode the video frame to provide an encoded video frame and upload the encoded video frame to the media mastering system.

公开(公告)号：US12099547B2

公开(公告)日：2024-09-24

申请号：US18139367

申请日：2023-04-26

Applicant: Snap Inc.

Inventor： Jeremy Voss ,  Victor Shaburov ,  Aleksandr Mashrabov ,  Dmitriy Matov ,  Hanna Rulevska ,  Dmytro Ishchenko

IPC: G06F16/732 ,  G06F16/71 ,  H04L51/10

CPC classification number: G06F16/7328 ,  G06F16/71 ,  H04L51/10

Abstract: Systems and methods for searching and ranking videos are provided. An example method includes receiving an input from a user via a multimedia messaging application (MMA), selecting, from a database configured to store videos, a subset of videos based on the input and a predetermined rule, rendering, via the MMA, the subset of videos, determining that the user has viewed a video from the subset of videos, determining whether the user has shared, via the MMA, the viewed video, updating a log based on information concerning the subset of videos and the viewed video, and updating, based on the log, a model of the predetermined rule for selecting the videos. The model is trained based on pairs of first videos and second videos, where the first videos have been viewed and shared by the user and the second videos have been viewed but not shared by the user.

公开(公告)号：US12019678B2

公开(公告)日：2024-06-25

申请号：US17881151

申请日：2022-08-04

Applicant: Electronics and Telecommunications Research Institute

Inventor： Jin Young Moon ,  Jung Kyoo Shin

IPC: G06F7/00 ,  G06F16/732 ,  G06F40/279 ,  G06F40/30 ,  G06V10/82 ,  G06V20/40

CPC classification number: G06F16/7328 ,  G06F40/279 ,  G06F40/30 ,  G06V10/82 ,  G06V20/46 ,  G06V20/49

Abstract: Provided is a method of detecting a semantics section in a video. The method includes extracting all video features by inputting an inputted video to a pre-trained first deep neural network algorithm, extracting a query sentence feature by inputting an inputted query sentence to a pre-trained second deep neural network algorithm, generating video-query relation integration feature information in which all of the video features and the query sentence feature have been integrated by inputting all of the video features and the query sentence feature to a plurality of scaled-dot product attention layers, and estimating a video segment corresponding to the query sentence in the video based on the video-query relation integration feature information.

公开(公告)号：US20240135802A1

公开(公告)日：2024-04-25

申请号：US18205343

申请日：2023-06-01

Applicant: B&W Group Ltd.

Inventor： Gaylord Yu

IPC: G08C17/00 ,  G06F16/732 ,  H04N21/41 ,  H04N21/422 ,  H04N21/4223 ,  H04N21/436 ,  H04N21/4363 ,  H04N21/439 ,  H04N21/44 ,  H04N21/472 ,  H04N21/482

CPC classification number: G08C17/00 ,  G06F16/7328 ,  H04N21/41265 ,  H04N21/42204 ,  H04N21/4223 ,  H04N21/43615 ,  H04N21/4363 ,  H04N21/4394 ,  H04N21/44008 ,  H04N21/472 ,  H04N21/482 ,  G06V30/10 ,  G08C2201/20

Abstract: An electronic device that obtains a set of remote-control commands is described. During operation, the electronic device may receive an image associated with a second electronic device, where a brand and a model of the second electronic device are initially unknown to the electronic device. Then, the electronic device may perform image analysis on the image to determine at least the brand of the second electronic device. Moreover, the electronic device may access, based at least in part on the determined brand, the set of remote-control commands that are associated with the second electronic device. Next, the electronic device may store the set of remote-control commands in memory. Subsequently, when the electronic device receives user-interface activity information associated with a portable electronic device that specifies selection of the second electronic device, the electronic device may provide the set of remote-control commands to the second electronic device.

公开(公告)号：US20240089522A1

公开(公告)日：2024-03-14

申请号：US18461768

申请日：2023-09-06

Applicant: TAP Technologies SA

Inventor： Valery Ushakov ,  Andrey Tatarinov ,  Aleksandr Kozlov ,  Anna Zakutniaia

IPC: H04N21/254 ,  G06F16/732 ,  G06F16/783 ,  G06Q30/0601 ,  H04N21/2187 ,  H04N21/4725

CPC classification number: H04N21/2542 ,  G06F16/7328 ,  G06F16/7837 ,  G06Q30/0601 ,  H04N21/2187 ,  H04N21/4725

Abstract: A system and method are suitable for product placement. The system having a user device including a touch-sensitive screen, a camera for capturing video, and a wireless telecommunication module. The mobile device configured present to the user, via the touch-sensitive screen, a live video feed of the view of the camera, receive from the user, input selections to initiate a video search based on the view of the camera, send a video search query to a server that is based on images captured by the camera, receive a response to the video search query from the server and display items appropriate to the view of the camera.

公开(公告)号：US11699341B2

公开(公告)日：2023-07-11

申请号：US17587039

申请日：2022-01-28

Applicant: B&W Group Ltd.

Inventor： Gaylord Yu

IPC: H04N21/41 ,  G08C17/00 ,  H04N21/4363 ,  H04N21/422 ,  H04N21/439 ,  H04N21/436 ,  H04N21/472 ,  H04N21/44 ,  H04N21/482 ,  G06F16/732 ,  H04N21/4223 ,  G06V30/10

CPC classification number: G08C17/00 ,  G06F16/7328 ,  H04N21/41265 ,  H04N21/4223 ,  H04N21/42204 ,  H04N21/4363 ,  H04N21/4394 ,  H04N21/43615 ,  H04N21/44008 ,  H04N21/472 ,  H04N21/482 ,  G06V30/10 ,  G08C2201/20 ,  H04N21/4126

Abstract: An electronic device that obtains a set of remote-control commands is described. During operation, the electronic device may receive an image associated with a second electronic device, where a brand and a model of the second electronic device are initially unknown to the electronic device. Then, the electronic device may perform image analysis on the image to determine at least the brand of the second electronic device. Moreover, the electronic device may access, based at least in part on the determined brand, the set of remote-control commands that are associated with the second electronic device. Next, the electronic device may store the set of remote-control commands in memory. Subsequently, when the electronic device receives user-interface activity information associated with a portable electronic device that specifies selection of the second electronic device, the electronic device may provide the set of remote-control commands to the second electronic device.

公开(公告)号：US11687589B2

公开(公告)日：2023-06-27

申请号：US17556576

申请日：2021-12-20

Applicant: Rovi Guides, Inc.

Inventor： Durga Prasad Pulicharla ,  Madhusudhan Srinivasan

IPC: G06F3/048 ,  G06F16/738 ,  G06F16/783 ,  G06F3/04883 ,  G06F16/732

CPC classification number: G06F16/738 ,  G06F3/04883 ,  G06F16/7328 ,  G06F16/783

Abstract: Methods and systems for auto-populating image metadata are described herein. The system receives or accesses an image. The system then generates a link to a video having a frame that corresponds to the image. To generate the link, the system searches for a video having a frame comprising a portion of the image and generates the link such that the link comprises a timestamp of the frame. The system then modifies the metadata of the image to include the link. Once a user interaction with the image is detected, the system may follow the link to generate for display the video beginning at the timestamp.

公开(公告)号：US11644950B2

公开(公告)日：2023-05-09

申请号：US16200142

申请日：2018-11-26

Applicant: Google LLC

Inventor： Aaron Joseph Wheeler ,  Chris Lauritzen

IPC: G06F3/0482 ,  G06F3/0485 ,  G06F3/0481 ,  G06F16/44 ,  G06F16/25 ,  G06F16/438 ,  G06F3/04817 ,  G06F16/74 ,  G06F16/432 ,  G06F16/738 ,  G06F16/732 ,  G06F3/0488

CPC classification number: G06F3/0482 ,  G06F3/0485 ,  G06F3/04817 ,  G06F16/252 ,  G06F16/438 ,  G06F16/44 ,  G06F16/743 ,  G06F3/0488 ,  G06F16/434 ,  G06F16/4387 ,  G06F16/739 ,  G06F16/7328

Abstract: A video playlist associated with a set of videos is distinguished in a graphical user interface using a dynamic thumbnail to represent the playlist. The dynamic thumbnail comprises a static portion comprising a first image associated with the set of videos and a dynamic portion comprising one or more second images associated with the set of videos. An image provided in the dynamic portion is configured to change while the first image remains the same in response to a shift in the graphical user interface that results in a change in position of the thumbnail about the user graphical user interface.

公开(公告)号：US20180060667A1

公开(公告)日：2018-03-01

申请号：US15685369

申请日：2017-08-24

Applicant: Snell Advanced Media Limited

Inventor： Jonathan Diggins

IPC: G06K9/00 ,  H04N17/02 ,  H04N5/04

CPC classification number: G06K9/00744 ,  G06F16/7328 ,  G06K9/00758 ,  G06K9/00765 ,  H04N5/04 ,  H04N17/02 ,  H04N21/23418

Abstract: A first sequence of video fingerprints at a first image repetition rate is compared with a second sequence of video fingerprints at a second, different image repetition rate. A converted sequence of fingerprints is generated from the first or second sequence of fingerprints by forming a combination of the values of a number of neighbouring fingerprints. The combination is a weighted average based on the temporal location of the respective neighbouring fingerprints in the first sequence of fingerprints with respect to the fingerprint in the converted sequence. A correlation is then performed between the converted sequence of fingerprints and the other sequence of fingerprints.

公开(公告)号：US20150286719A1

公开(公告)日：2015-10-08

申请号：US14244155

申请日：2014-04-03

Applicant: SONY CORPORATION

Inventor： SRIRAM SAMPATHKUMARAN

IPC: G06F17/30 ,  G06F3/0484

CPC classification number: G06F16/7335 ,  G06F3/04842 ,  G06F3/04845 ,  G06F3/0486 ,  G06F16/7328 ,  G06F16/739 ,  G06F16/784

Abstract: A user can enter a name of one or more people to search in video or drag and drop around an image of a person or persons to be searched, and a computer tags video frames in which face recognition indicates that the person is present. All of the segments containing the person may be stitched together, omitting intervening segments not containing the person's image, or all segments with the person's image in them can be omitted and the remaining segments stitched together.

Abstract translation: 用户可以输入一个或多个人的名称来在视频中进行搜索，或者拖放要搜索的个人的图像，并且计算机标记面部识别表示该人在场的视频帧。 包含该人的所有段可以被缝合在一起，省略不包含该人的图像的中间段，或者可以省略其中的人的图像的所有段，并且剩余的段被缝合在一起。