Recognizing minutes-long activities in videos

A method for classifying subject activities in videos includes learning latent (previously generated) concepts that are analogous to nodes of a graph to be generated for an activity in a video. The method also includes receiving video segments of the video. A similarity between the video segments an...

Full description

Saved in:
Bibliographic Details
Main Authors Gavves, Efstratios, Hussein, Noureldien Mahmoud Elsayed, Smeulders, Arnold Wilhelmus Maria
Format Patent
LanguageEnglish
Published 13.09.2022
Subjects
Online AccessGet full text

Cover

Loading…
Abstract A method for classifying subject activities in videos includes learning latent (previously generated) concepts that are analogous to nodes of a graph to be generated for an activity in a video. The method also includes receiving video segments of the video. A similarity between the video segments and the previously generated concepts is measured to obtain segment representations as a weighted set of latent concepts. The method further includes determining a relationship between the segment representations and their transitioning pattern over time to determine a reduced set of nodes and/or edges for the graph. The graph of the activity in the video represented by the video segments is generated based on the reduced set of nodes and/or edges. The nodes of the graph are represented by the latent concepts. Subject activities in the video are classified based on the graph.
AbstractList A method for classifying subject activities in videos includes learning latent (previously generated) concepts that are analogous to nodes of a graph to be generated for an activity in a video. The method also includes receiving video segments of the video. A similarity between the video segments and the previously generated concepts is measured to obtain segment representations as a weighted set of latent concepts. The method further includes determining a relationship between the segment representations and their transitioning pattern over time to determine a reduced set of nodes and/or edges for the graph. The graph of the activity in the video represented by the video segments is generated based on the reduced set of nodes and/or edges. The nodes of the graph are represented by the latent concepts. Subject activities in the video are classified based on the graph.
Author Hussein, Noureldien Mahmoud Elsayed
Gavves, Efstratios
Smeulders, Arnold Wilhelmus Maria
Author_xml – fullname: Gavves, Efstratios
– fullname: Hussein, Noureldien Mahmoud Elsayed
– fullname: Smeulders, Arnold Wilhelmus Maria
BookMark eNrjYmDJy89L5WTQDUpNzk_Py6zKzEtXyM3MKy1JLdbNyQdyEpNLMssySzJTixUy8xTKMlNS84t5GFjTEnOKU3mhNDeDoptriLOHbmpBfnxqcUFicmpeakl8aLChoYmJsamhiZORMTFqAOtDLGs
ContentType Patent
DBID EVB
DatabaseName esp@cenet
DatabaseTitleList
Database_xml – sequence: 1
  dbid: EVB
  name: esp@cenet
  url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Chemistry
Sciences
Physics
ExternalDocumentID US11443514B2
GroupedDBID EVB
ID FETCH-epo_espacenet_US11443514B23
IEDL.DBID EVB
IngestDate Fri Jul 19 14:42:26 EDT 2024
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-epo_espacenet_US11443514B23
Notes Application Number: US202016827342
OpenAccessLink https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220913&DB=EPODOC&CC=US&NR=11443514B2
ParticipantIDs epo_espacenet_US11443514B2
PublicationCentury 2000
PublicationDate 20220913
PublicationDateYYYYMMDD 2022-09-13
PublicationDate_xml – month: 09
  year: 2022
  text: 20220913
  day: 13
PublicationDecade 2020
PublicationYear 2022
RelatedCompanies QUALCOMM Technologies, Inc
RelatedCompanies_xml – name: QUALCOMM Technologies, Inc
Score 3.4212203
Snippet A method for classifying subject activities in videos includes learning latent (previously generated) concepts that are analogous to nodes of a graph to be...
SourceID epo
SourceType Open Access Repository
SubjectTerms CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
HANDLING RECORD CARRIERS
PHYSICS
PRESENTATION OF DATA
RECOGNITION OF DATA
RECORD CARRIERS
Title Recognizing minutes-long activities in videos
URI https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220913&DB=EPODOC&locale=&CC=US&NR=11443514B2
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1bS8MwFD6MeX3Tqui8UEH6Fty6trYPReiNIezCtsreRppm0KHtsJ2Cv96T2Dlf9DEnEE4SziXJd74A3DGd8hT3mdjMXBBBgU5shy4INVjKHJt3EvnHUn9g9WLjaWbOGrDc1MJIntAPSY6IFsXQ3ivpr1fbS6xAYivL-yRDUfEYTd1Aq0_Hui5oLrXAc8PRMBj6mu-78UQbjF1M-w0BWvfQXe8I2i3Bsx8-e6IqZfU7pERHsDvC0fLqGBo8V-DA3_y8psB-v37wVmBPIjRZicLaCssTIONv1M8nhh31NcvXmC6SlwIbokrhXXKkqlmuihK7ojyF2yic-j2CGsx_pjuPJ1tlu2fQzIucn4OKUcVKuJVapuDQozp9SBzHoKxtpw63WPsCWn-P0_qv8xIOxdIJFESnewXN6m3NrzHUVsmNXKMv8pyCzg
link.rule.ids 230,308,780,885,25564,76547
linkProvider European Patent Office
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1bT8IwFD4heME3nRrF20zM3hphbGN7WEzYIKhsENgMb2TrSoLRjbihib_e0zrEF31smzSnbc6l7Xe-A3BD1YgleM7EpPqccAp0YlrRnEQaTahlsmYsaix5vtEPtYepPq3A8zoXRvCEfghyRNQoivpeCHu93DxiuQJbmd_GC-zK7nqB7Srl7VhVOc2l4nbs7mjoDh3FcexwovhjG8N-jYPWO2iut9q84i4PnZ46PCtl-dul9PZhe4SzpcUBVFgqQc1ZV16TYNcrP7wl2BEITZpjZ6mF-SGQ8Tfq5xPdjvy6SFcYLpKXDBs8S-FdcKTKi1TmKXZZfgTXvW7g9AlKMPtZ7iycbIRtHUM1zVJ2AjJ6FSNmRmLonEMvUqN2bFlaRBtmYjGDNk6h_vc89f8Gr6DWD7zBbHDvP57BHt9Gjohots6hWryt2AW63SK-FPv1BT3lhb8
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=Recognizing+minutes-long+activities+in+videos&rft.inventor=Gavves%2C+Efstratios&rft.inventor=Hussein%2C+Noureldien+Mahmoud+Elsayed&rft.inventor=Smeulders%2C+Arnold+Wilhelmus+Maria&rft.date=2022-09-13&rft.externalDBID=B2&rft.externalDocID=US11443514B2