公开(公告)号：US12158913B2

公开(公告)日：2024-12-03

申请号：US18298208

申请日：2023-04-10

Applicant: Electronics and Telecommunications Research Institute

Inventor： Joon Soo Kim ,  Joung II Yun ,  Geun Taek Lim ,  Won Jo ,  Yu Kyung Choi

IPC: G06F16/50 ,  G06F16/583 ,  G06F16/70 ,  G06F16/732 ,  G06F16/783 ,  G06V10/771 ,  G06V10/82

Abstract: The present disclosure discloses an image/video feature descriptor extraction method and apparatus for image/video search. An image/video feature descriptor extraction method may comprise obtaining a search requested image/video from a user, performing spatio-temporal transformation on the search requested image/video, extracting a feature map from the image/video subjected to the spatio-temporal transformation, and extracting an image/video feature descriptor by applying TNIP (Temporal Nested Invariance Pooling) to the feature map.

公开(公告)号：US12137269B2

公开(公告)日：2024-11-05

申请号：US18352927

申请日：2023-07-14

Applicant: Comcast Cable Communications, LLC

Inventor： James Cahill

IPC: H04N21/442 ,  G06F16/40 ,  G06F16/535 ,  G06F16/70 ,  H04N21/25 ,  H04N21/258

Abstract: Methods and systems are described for providing optimal representations of content. A user interface may present content based on one or more images representing the content. User interactions associated with the content may be tracked based on which of the one or more images was used to represent the content. Statistical information may be tracked to determine which groups of users respond to particular images used to represent content. The statistical information may be used to select which images are used to represent the content for additional users.

公开(公告)号：US12086179B2

公开(公告)日：2024-09-10

申请号：US18455189

申请日：2023-08-24

Applicant: Beijing Bytedance Network Technology Co., Ltd.

Inventor： Ping Wu ,  Ruiqi Peng ,  Kai Wu

IPC: G06F16/70 ,  G06F16/732 ,  G06F16/735 ,  G06F16/738 ,  G06F16/74 ,  G06F16/78

CPC classification number: G06F16/735 ,  G06F16/732 ,  G06F16/7335 ,  G06F16/738 ,  G06F16/74 ,  G06F16/7867

Abstract: The present disclosure provides a method and apparatus for information display, and a non-volatile computer storage medium. The method includes: displaying search prompt information in response to a trigger operation for review content corresponding to a video; and displaying a search result page in response to a selection operation for the search prompt information.

公开(公告)号：US12045281B2

公开(公告)日：2024-07-23

申请号：US17985115

申请日：2022-11-10

Applicant: Twelve Labs, Inc.

Inventor： Seung Joon Lee ,  Haram Jo ,  Eunkyung Yoon ,  Soyoung Lee ,  Jae Sung Lee

IPC: G06F16/70 ,  G06F16/738 ,  G06F16/783

CPC classification number: G06F16/738 ,  G06F16/784 ,  G06F16/7844

Abstract: Provided is a method of providing a user interface for video retrieval performed by a computing device, the method including: receiving a search query, providing a search result interface displaying at least one search video content and search section searched by the search query, wherein the search video content and the search section are related with at least one of a plurality of video semantic search attributes corresponding to the search query, and providing a timeline view interface for the search video content when it is determined to display the search result interface according to a timeline view mode, wherein the timeline view interface has a visual characteristic indicating the degree of relevance to at least one of the plurality of video semantic search attributes corresponding to the search query.

公开(公告)号：US12015659B2

公开(公告)日：2024-06-18

申请号：US17680438

申请日：2022-02-25

Applicant: International Business Machines Corporation

Inventor： Manjit Singh Sodhi ,  Rahul Jain ,  Shashank Mujumdar ,  Nitin Gupta ,  Prerna Agarwal

IPC: H04L65/70 ,  G06F16/22 ,  G06F16/70 ,  H04L65/611 ,  H04L65/612 ,  H04N21/236 ,  H04N21/266

CPC classification number: H04L65/70 ,  G06F16/70 ,  H04L65/611 ,  H04L65/612 ,  H04N21/236 ,  H04N21/266 ,  G06F16/2264

Abstract: A system may include a memory and a processor in communication with the memory. The processor may be configured to perform operations. The operations may include extracting a first multiple dimensional dataset and a second multiple dimensional dataset and encoding the first multiple dimensional dataset into a first encoded dataset and the second multiple dimensional dataset into a second encoded dataset. The operations may include combining the first encoded dataset and the second encoded dataset into a combined encoded dataset and conveying the combined encoded dataset to a user.

公开(公告)号：US11966440B2

公开(公告)日：2024-04-23

申请号：US17500455

申请日：2021-10-13

Applicant: eBay Inc.

Inventor： Dingxian Wang ,  Hongxu Chen ,  Guandong Xu ,  Li He

IPC: G06F16/70 ,  G06F16/74 ,  G06F16/78 ,  G06F16/783 ,  G06Q50/00

CPC classification number: G06F16/7867 ,  G06F16/743 ,  G06F16/7834 ,  G06F16/7844 ,  G06Q50/01

Abstract: A method for automatic metadata tag identification for videos is described. Content features are extracted from a video into respective data structures. The extracted content features are from at least two different feature modalities. The respective data structures are encoded into a common data structure using an encoder of a recurrent neural network (RNN) model. The common data structure is decoded using a decoder of the RNN model to identify content platform metadata tags to be associated with the video on a social content platform. Decoding is based on group tag data for users of the social content platform that identifies groups of the users and corresponding group metadata tags of interest for the groups of users.

公开(公告)号：US20240056628A1

公开(公告)日：2024-02-15

申请号：US18373497

申请日：2023-09-27

Applicant: TiVo Solutions Inc.

Inventor： Mark Berner ,  David Chamberlin ,  Kevin P. Smith

IPC: H04N21/43 ,  G06F16/70 ,  G06F16/901 ,  H04N21/2343 ,  H04N21/235 ,  H04N21/435 ,  H04N21/432 ,  H04N21/81 ,  H04N21/4545 ,  H04N21/845 ,  H04N21/44 ,  H04N21/472 ,  H04N21/4147 ,  H04N21/442 ,  H04N21/8352

CPC classification number: H04N21/43074 ,  G06F16/70 ,  G06F16/9014 ,  H04N21/23439 ,  H04N21/2358 ,  H04N21/2353 ,  H04N21/4358 ,  H04N21/4325 ,  H04N21/235 ,  H04N21/435 ,  H04N21/812 ,  H04N21/45457 ,  H04N21/8455 ,  H04N21/44008 ,  H04N21/47217 ,  H04N21/4147 ,  H04N21/432 ,  H04N21/44209 ,  H04N21/8352 ,  H04N21/8456 ,  H04N21/433

Abstract: Tag data is created from in-band data in a media content item by a remote location while the media content item is being broadcasted by a content provider and received by the remote location. The tag data identifies locations in the media content item which enables media devices to accurately jump to particular locations in the media content item based on the tag data.

公开(公告)号：US11895186B2

公开(公告)日：2024-02-06

申请号：US17094975

申请日：2020-11-11

Applicant: Sinclair Broadcast Group, Inc.

Inventor： Benjamin A. Miller ,  Kevin J. Cotlove ,  Michael E. Bouchard ,  Paul D. Norton ,  David Thornton ,  Jonathan D. Kersten ,  Jason D. Justman

IPC: G06F16/40 ,  G06F16/958 ,  G06F16/483 ,  H04L67/02 ,  H04L67/1097 ,  G06F16/70 ,  H04L67/10 ,  G06F16/957 ,  H04L67/55 ,  H04L67/60 ,  G06F16/63 ,  G06F16/532 ,  G06F16/50 ,  G06F16/60 ,  G06F16/954 ,  H04L67/5682

CPC classification number: H04L67/1097 ,  G06F16/40 ,  G06F16/483 ,  G06F16/532 ,  G06F16/63 ,  G06F16/70 ,  G06F16/957 ,  G06F16/958 ,  H04L67/10 ,  H04L67/55 ,  H04L67/60 ,  G06F16/50 ,  G06F16/60 ,  G06F16/954 ,  H04L67/02 ,  H04L67/5682

Abstract: Organizing and publishing content in a content management system wherein content, including text, images and video, is received and segmented into content atoms. One or more tags are associated with the content atoms to allow device specific presentation of the content atoms.

公开(公告)号：US20240022789A1

公开(公告)日：2024-01-18

申请号：US18352927

申请日：2023-07-14

Applicant: Comcast Cable Communications, LLC

Inventor： James CAHILL

IPC: H04N21/442 ,  H04N21/258 ,  G06F16/40 ,  G06F16/70 ,  G06F16/535 ,  H04N21/25

CPC classification number: H04N21/44226 ,  H04N21/25866 ,  G06F16/40 ,  G06F16/70 ,  G06F16/535 ,  H04N21/252

Abstract: Methods and systems are described for providing optimal representations of content. A user interface may present content based on one or more images representing the content. User interactions associated with the content may be tracked based on which of the one or more images was used to represent the content. Statistical information may be tracked to determine which groups of users respond to particular images used to represent content. The statistical information may be used to select which images are used to represent the content for additional users.

公开(公告)号：US11868398B1

公开(公告)日：2024-01-09

申请号：US17850646

申请日：2022-06-27

Applicant: Tubular Labs, Inc.

Inventor： Dmytro Popovych ,  Michael Kamprath ,  Andrew Huson

IPC: G06F16/70 ,  G06F16/735 ,  G06F16/75 ,  G06F16/71

CPC classification number: G06F16/735 ,  G06F16/71 ,  G06F16/75

Abstract: Dynamic determination of video correlation is disclosed, including: obtaining a plurality of recorded video interactions; obtaining a plurality of recorded non-video interactions; storing, at a database, event data determined based at least in part on the plurality of recorded video interactions and the plurality of recorded non-video interactions; and determining a subset of the event data that comprises correlations between a video and non-video interactions.