UNSUPERVISED LEARNING OF OBJECT KEYPOINT LOCATIONS IN IMAGES THROUGH TEMPORAL TRANSPORT OR SPATIO-TEMPORAL TRANSPORT

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for unsupervised learning of object keypoint locations in images. In particular, a keypoint extraction machine learning model having a plurality of keypoint model parameters is trained to receive an input...

Full description

Saved in:
Bibliographic Details
Main Authors Kulkarni, Tejas Dattatraya, Gupta, Ankush
Format Patent
LanguageEnglish
Published 07.07.2022
Subjects
Online AccessGet full text

Cover

Loading…
Abstract Methods, systems, and apparatus, including computer programs encoded on computer storage media, for unsupervised learning of object keypoint locations in images. In particular, a keypoint extraction machine learning model having a plurality of keypoint model parameters is trained to receive an input image and to process the input image in accordance with the keypoint model parameters to generate a plurality of keypoint locations in the input image. The machine learning model is trained using either temporal transport or spatio-temporal transport.
AbstractList Methods, systems, and apparatus, including computer programs encoded on computer storage media, for unsupervised learning of object keypoint locations in images. In particular, a keypoint extraction machine learning model having a plurality of keypoint model parameters is trained to receive an input image and to process the input image in accordance with the keypoint model parameters to generate a plurality of keypoint locations in the input image. The machine learning model is trained using either temporal transport or spatio-temporal transport.
Author Gupta, Ankush
Kulkarni, Tejas Dattatraya
Author_xml – fullname: Kulkarni, Tejas Dattatraya
– fullname: Gupta, Ankush
BookMark eNqNi70KwjAURjvo4N87XHAu1EjBNdbbNtrmhuRGcCpF4iRtoX1_VHBzcfoOnPMto1nXd2ERTV47b9BelcMTVCitVroAyoGOZ8wYLngzpDRDRZlkRdqB0qBqWaADLi35ogTG2pCVFbCV2r2RgSw48znEv3IdzR_tcwyb766ibY6clXEY-iaMQ3sPXZga70QihNil6SGRu_1_1QuNwTx5
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 US2022215580A1
GroupedDBID EVB
ID FETCH-epo_espacenet_US2022215580A13
IEDL.DBID EVB
IngestDate Fri Jul 19 13:04:47 EDT 2024
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-epo_espacenet_US2022215580A13
Notes Application Number: US202017608620
OpenAccessLink https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220707&DB=EPODOC&CC=US&NR=2022215580A1
ParticipantIDs epo_espacenet_US2022215580A1
PublicationCentury 2000
PublicationDate 20220707
PublicationDateYYYYMMDD 2022-07-07
PublicationDate_xml – month: 07
  year: 2022
  text: 20220707
  day: 07
PublicationDecade 2020
PublicationYear 2022
RelatedCompanies DeepMind Technologies Limited
RelatedCompanies_xml – name: DeepMind Technologies Limited
Score 3.413782
Snippet Methods, systems, and apparatus, including computer programs encoded on computer storage media, for unsupervised learning of object keypoint locations in...
SourceID epo
SourceType Open Access Repository
SubjectTerms CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
Title UNSUPERVISED LEARNING OF OBJECT KEYPOINT LOCATIONS IN IMAGES THROUGH TEMPORAL TRANSPORT OR SPATIO-TEMPORAL TRANSPORT
URI https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220707&DB=EPODOC&locale=&CC=US&NR=2022215580A1
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfR1dS8Mw8Bh-v-lU_JgSUPpW7FbbzochXZuu1TUp_RjzaaxpC4J0w1X8-6ah04GwtyRHDu7gch-5D4D7QtFSvSgMmfWZKnONp8lPWZpxwVO7WaHp866YReAT3U0eX6batAUf61oY0Sf0WzRH5BLFuLxX4r1e_gWxbJFbuXpI3_nR4tmJB7bUeMe9Xt29RrKHAxxQm1qSZQ2SSCKhgHHtpvUVk_tKu9yQNuoEMDwZ1nUpy02l4hzDXsDxldUJtPKyDYfWevZaGw785su7DfsiR5Ot-GEjh6tTqBISJQEOJ16EbTTGZkg8MkLUQVTML0Gv-C2gHonRmDaVwsgjyPPNEY5Q7IY0Gbkoxn4dpBqjODRJxJcxoiGKgvqC_B94BncOji1X5oTMfvk2S6JNqtVz2CkXZX4BiM25EcKMTO3q3EHIWF9Rc2YUWqYrabdQ9UvobMN0tR18DUf1VuS0Gh3YqT6_8huuuav0VjD8B5z0k3Q
link.rule.ids 230,309,783,888,25578,76884
linkProvider European Patent Office
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfR1da4MwMJR9dW9bt7GPbgts-CbTOq17KMNqrK4aRWPpnkqNCoNhy-rY31_M7FYY9C3ckYM7uNxH7gOA-0JSU60o-iLVqSIyi6eKT1maMcVT5KxQtbnMdxH4WHOSx5epOm2B93UvDJ8T-sWHIzKNokzfK_5eL_-SWBavrVw9pG8MtHi2ycASmui416un1wjWcIDCwApMwTQHSSzgiOOYdVN1yWCx0i5zsvV60j6aDOu-lOWmUbGPwF7I6JXVMWjlZQe0zfXutQ448Jsv7w7Y5zWadMWAjR6uTkCV4DgJUTRxY2RBDxkRdvEIBjYM-P4SOEavYeBiAr2g6RSGLoaub4xQDIkTBcnIgQT5dZLKgyQycMyOBAYRjMP6gvgfeQrubERMR2SMzH7lNkviTa6VM7BTLsr8HEA6Z04I7WeKrLEAIaO6pOS0X6iZJqVyoWgXoLuN0uV29C1oO8T3Zp6Lx1fgsN7P_pOz6IKd6uMzv2ZWvEpvuPC_Aa-xllk
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=UNSUPERVISED+LEARNING+OF+OBJECT+KEYPOINT+LOCATIONS+IN+IMAGES+THROUGH+TEMPORAL+TRANSPORT+OR+SPATIO-TEMPORAL+TRANSPORT&rft.inventor=Kulkarni%2C+Tejas+Dattatraya&rft.inventor=Gupta%2C+Ankush&rft.date=2022-07-07&rft.externalDBID=A1&rft.externalDocID=US2022215580A1