公开(公告)号：US12217771B2

公开(公告)日：2025-02-04

申请号：US18097695

申请日：2023-01-17

Applicant: Adeia Media Holdings LLC

Inventor： Erik Van de Pol

IPC: G11B27/34 ,  G06F16/738 ,  G11B27/10 ,  H04N5/783 ,  H04N21/432 ,  H04N21/44

Abstract: Systems and procedures for transforming video into a condensed visual representation. An example procedure may include receiving video comprised of a plurality of frames. For each frame, the example procedure may create a first representation, reduced in one dimension, wherein a visual property of each pixel of the first representation is assigned by aggregating a visual property of the pixels of the frame having the same position in the unreduced dimension. The example procedure may further form a condensed visual representation including the first representations aligned along the reduced dimension according to an order of the frames in the video.

公开(公告)号：US12164564B1

公开(公告)日：2024-12-10

申请号：US17568746

申请日：2022-01-05

Applicant: Waylens, Inc.

Inventor： Jeffery R. Campbell

IPC: G06F16/78 ,  B60R1/00 ,  G06F16/738 ,  G06F16/783 ,  G06V20/56 ,  G06V20/58 ,  G06V20/62 ,  H04N7/18 ,  G05D1/00

Abstract: An apparatus comprising a processor and a memory. The processor may be configured to (i) receive video frames captured by a capture device and (ii) perform video analysis on the video frames to extract metadata corresponding to objects detected in the video frames. The memory may be configured to (i) store co-ordinates corresponding to a plurality of regions of the video frames and (ii) provide temporary storage for the video frames to enable the processor to perform the video analysis. The video analysis may perform a different amount of processing for detecting the objects on each of the plurality of regions. One of the regions corresponds to a portion of the video frame comprising a hood of a vehicle.

公开(公告)号：US12155914B2

公开(公告)日：2024-11-26

申请号：US18532114

申请日：2023-12-07

Applicant: Adeia Guides Inc.

Inventor： Reda Harb

IPC: H04N21/8549 ,  G06F16/738 ,  H04N21/431 ,  H04N21/432 ,  H04N21/466

Abstract: Systems and methods are provided herein for identifying a playlist of highlights to use for refreshing a user on a plot related to a media asset the user has requested to access based on how long it has been since the user last saw related programming. The media guidance application may receive a request from a user to access a media asset and may determine whether the user previously consumed a related media asset to the media asset. The media guidance application may determine whether a period of time between receiving the request and a time when the user previously consumed the related media asset exceeds a threshold period of time. If the period of time does not exceed the threshold, the media guidance application may play back a predefined playlist of highlights, and if it exceeds the threshold, the media guidance application may play back a customized playlist of highlights.

公开(公告)号：US20240364961A1

公开(公告)日：2024-10-31

申请号：US18770050

申请日：2024-07-11

Applicant: Rovi Guides, Inc.

Inventor： David D. Shoop

IPC: H04N21/436 ,  G06F16/73 ,  G06F16/738 ,  H04N7/18 ,  H04N21/41 ,  H04N21/431 ,  H04N21/442 ,  H04N21/462 ,  H04N21/472 ,  H04N21/4782 ,  H04N21/482 ,  H04N21/485

CPC classification number: H04N21/43615 ,  G06F16/73 ,  G06F16/738 ,  H04N21/4108 ,  H04N21/4126 ,  H04N21/41265 ,  H04N21/4131 ,  H04N21/4314 ,  H04N21/4316 ,  H04N21/44227 ,  H04N21/44231 ,  H04N21/4622 ,  H04N21/472 ,  H04N21/4782 ,  H04N21/4821 ,  H04N21/4823 ,  H04N21/4858 ,  H04N7/181

Abstract: Systems and methods for navigating through activity information using a media guidance application are provided. An Internet appliance is integrated with a plurality of content sources accessible to user equipment. A simultaneous display of a first plurality of media asset listings, corresponding to a first plurality of media assets transmitted by each of the plurality of content sources during a first time interval that includes the present time, and information received from the Internet appliance is generated. In response to a user request to navigate to a second time interval that precedes the present time, a simultaneous display of a second plurality of media asset listings, corresponding to a second plurality of media assets that were transmitted by each of the plurality of content sources during the second time interval, and a timeline that includes indicators representing activity detected by the Internet appliance during the second time interval is generated.

公开(公告)号：US20240320958A1

公开(公告)日：2024-09-26

申请号：US18186467

申请日：2023-03-20

Applicant: Netflix, Inc.

Inventor： Amirreza Ziai ,  Aneesh Vartakavi ,  Kelli Griggs ,  Yvonne Sylvia Jukes ,  Sean Ferris ,  Eugene Lok ,  Alejandro Alonso

IPC: G06V10/774 ,  G06F16/735 ,  G06F16/738 ,  G06F16/75 ,  G06V10/776 ,  G06V10/94 ,  G06V20/40

CPC classification number: G06V10/774 ,  G06F16/735 ,  G06F16/738 ,  G06F16/75 ,  G06V10/776 ,  G06V10/945 ,  G06V20/41 ,  G06V20/49

Abstract: The disclosed computer-implemented methods and systems include implementations that automatically generate and train a video clip classifier model to identify video clips that respond to a specific search query for a desired depiction that can include abstract, context-dependent, and/or subjective terms. For example, the methods and systems described herein generate and update a digital content understanding graphical user interface to facilitate the process of generating a corpus of training digital video clips, training a video clip classifier model with the training digital video clips, and applying the video clip classifier model to new digital video clips. Various other methods, systems, and computer-readable media are also disclosed.

公开(公告)号：US20240320266A1

公开(公告)日：2024-09-26

申请号：US18573281

申请日：2023-05-09

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Ying YAN ,  Ping LI ,  Hu LI

IPC: G06F16/78 ,  G06F16/738 ,  H04N21/232 ,  H04N21/431 ,  H04N21/81

CPC classification number: G06F16/7867 ,  G06F16/738 ,  H04N21/232 ,  H04N21/4318 ,  H04N21/8113

Abstract: The invention relate to video editing template search method, apparatus, electronic device and storage medium, wherein the method can acquire a search keyword input by a user, perform matching according to the search keyword to obtain a target music and a first template video; wherein the target music matches with the search keyword, the first template video is video edited by using a first editing template, and then present the user the first template video and the target music aggregately in a search result page in the form of card.

公开(公告)号：US12086180B2

公开(公告)日：2024-09-10

申请号：US17466491

申请日：2021-09-03

Applicant: Dice Corporation

Inventor： Gerald Corrion ,  Clifford Dice ,  Kevin Kilborn ,  Abdulrahman Zaiter

IPC: G06F16/73 ,  G06F3/0482 ,  G06F16/738 ,  G06F16/74 ,  G11B27/10 ,  H04N5/77

CPC classification number: G06F16/739 ,  G06F3/0482 ,  G06F16/743 ,  G11B27/102 ,  H04N5/77

Abstract: A method for searching a digital video recording is disclosed. The method includes receiving a video portion count associated with the digital video recording. The method further includes displaying in a graphical user interface (GUI) a number of sequential digital video images from the digital video recording in response to the video portion count to obtain displayed digital video images. The number of sequential digital video images is associated with a number of sequential portions of the digital video recording.

公开(公告)号：US20240221787A1

公开(公告)日：2024-07-04

申请号：US18484298

申请日：2023-10-10

Applicant: Robert Salem Abraham

Inventor： Robert Salem Abraham

IPC: G11B27/02 ,  G06N3/08 ,  G06F16/738 ,  G11B27/00 ,  G11B27/031 ,  G11B27/036 ,  H04N21/8549

CPC classification number: G11B27/02 ,  G06N3/08 ,  G06F16/739 ,  G11B27/00 ,  G11B27/031 ,  G11B27/036 ,  H04N21/8549

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for film-making using style transfer. One of the methods includes receiving an initial video comprising a sequence of initial video frames; receiving a selection of style images; for each initial video frame in the sequence of initial video frames, processing the initial video frame to generate a final video frame, the processing comprising: segmenting the initial video frame to generate a segmented video frame; generating a plurality of stylized video frames each according to a respective one of the style images; and generating a final video frame comprising, for each segment of the segmented video frame: determining a stylized video frame, extracting the respective segment from the determined stylized video frame, and inserting the extracted segment into the final video frame; and combining each generated final video frame in sequence to generate the final video.

公开(公告)号：US20240202240A1

公开(公告)日：2024-06-20

申请号：US18067294

申请日：2022-12-16

Applicant: Microsoft Technology Licensing, LLC

Inventor： Oron NIR ,  Ika BAR-MENACHEM ,  Inbal SAGIV

IPC: G06F16/735 ,  G06F16/71 ,  G06F16/738 ,  G06F16/783

CPC classification number: G06F16/735 ,  G06F16/71 ,  G06F16/738 ,  G06F16/784

Abstract: A video indexing system generates descriptive metadata for a video including identifiers for each of multiple detections that each correspond to a select one of multiple subjects that appear in the video. These detections are used to create relational graph data for the video, where the relational graph data includes nodes corresponding to each of the multiple subjects that appear in the video. A knowledge graph is queried with unique identifiers corresponding to the multiple subjects of the video to retrieve implicit relational data for each of the multiple subjects, and a merged relational graph is created by merging the implicit relational data retrieved from the knowledge graph with the relational graph data created for the video. A search engine uses the merged relational graph to identify video content relevant to a user query that is based on an implicit relation. Search results identifying the relevant content are presented on a user device.

公开(公告)号：US20240192834A1

公开(公告)日：2024-06-13

申请号：US18585524

申请日：2024-02-23

Applicant: Google LLC

Inventor： Christopher Charles Burns ,  George Alban Heitz, III ,  James Edward Stewart ,  Cameron Hill ,  Seungho Yang ,  Joe Delone Venters ,  William Alex Finlayson ,  Carsten Hinz ,  Timothy Samuel Psiaki ,  Nathan Scott Klee ,  Gregory Rourk Nelson ,  Kevin James Avery ,  Lawrence W. Neal ,  Martin Davidsson

IPC: G06F3/0482 ,  G05B15/02 ,  G06F3/04817 ,  G06F16/738 ,  G06F40/35 ,  G11B27/30 ,  H04L65/403 ,  H04L65/61 ,  H04N7/18 ,  H04N21/2387 ,  H04N21/4223 ,  H04N21/431 ,  H04N21/472 ,  H04N21/488 ,  H04N21/63 ,  H04N21/845 ,  H04N21/8549 ,  H04N21/858

CPC classification number: G06F3/0482 ,  G06F3/04817 ,  G06F16/739 ,  G11B27/3081 ,  H04L65/61 ,  H04N21/2387 ,  H04N21/4223 ,  H04N21/47217 ,  H04N21/488 ,  H04N21/8456 ,  H04N21/8549 ,  H04N21/858 ,  G05B15/02 ,  G06F40/35 ,  H04L65/403 ,  H04N7/186 ,  H04N21/4312 ,  H04N21/632

Abstract: A method at an electronic device with a display includes: displaying a user interface having a first region and a second region; receiving, and displaying in the first region of the user interface, a live video stream of a physical environment captured by a remote video camera; displaying, in the second region, a timeline corresponding to a timespan for a first portion of a duration during which the live video stream may have been recorded; in response to receiving a user interaction to move the timespan to a second portion of the duration, transitioning the displayed timeline to a new timeline that corresponds to the timespan for the second portion, and while transitioning, displaying, in the first region, a subset of video frames representing the first and/or second portion of the duration.