PREDICTING BODY MOTION

For each of a plurality of time steps: receive a reference joint pose of an articulated entity and receiving an indication that another joint of the articulated entity is unobserved or observed. Prompt a motion model using the reference joint pose and a mask token. The model predicts body motion com...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: CAMERON, Pashmina Jonathan, ALI AKBARIAN, Mohammand Sadegh, SALEH, Fatemehsadat
Format: Patent
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator CAMERON, Pashmina Jonathan
ALI AKBARIAN, Mohammand Sadegh
SALEH, Fatemehsadat
description For each of a plurality of time steps: receive a reference joint pose of an articulated entity and receiving an indication that another joint of the articulated entity is unobserved or observed. Prompt a motion model using the reference joint pose and a mask token. The model predicts body motion comprising a trajectory of the articulated entity and a pose of a plurality of joints of the articulated entity. The mask token represents the other joint and is temporally adaptable by: in response to receiving an indication that the other joint is unobserved, using information about the reference joint pose and a pose of the other joint from a previous time step; and in response to receiving an indication that the other joint is observed, using information about the reference joint pose and a pose of the other joint from the current time step.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2024264658A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2024264658A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2024264658A13</originalsourceid><addsrcrecordid>eNrjZBALCHJ18XQO8fRzV3Dyd4lU8PUP8fT342FgTUvMKU7lhdLcDMpuriHOHrqpBfnxqcUFicmpeakl8aHBRgZGJkZmJmamFo6GxsSpAgA29iAs</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>PREDICTING BODY MOTION</title><source>esp@cenet</source><creator>CAMERON, Pashmina Jonathan ; ALI AKBARIAN, Mohammand Sadegh ; SALEH, Fatemehsadat</creator><creatorcontrib>CAMERON, Pashmina Jonathan ; ALI AKBARIAN, Mohammand Sadegh ; SALEH, Fatemehsadat</creatorcontrib><description>For each of a plurality of time steps: receive a reference joint pose of an articulated entity and receiving an indication that another joint of the articulated entity is unobserved or observed. Prompt a motion model using the reference joint pose and a mask token. The model predicts body motion comprising a trajectory of the articulated entity and a pose of a plurality of joints of the articulated entity. The mask token represents the other joint and is temporally adaptable by: in response to receiving an indication that the other joint is unobserved, using information about the reference joint pose and a pose of the other joint from a previous time step; and in response to receiving an indication that the other joint is observed, using information about the reference joint pose and a pose of the other joint from the current time step.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; OPTICAL ELEMENTS, SYSTEMS, OR APPARATUS ; OPTICS ; PHYSICS</subject><creationdate>2024</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240808&amp;DB=EPODOC&amp;CC=US&amp;NR=2024264658A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240808&amp;DB=EPODOC&amp;CC=US&amp;NR=2024264658A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>CAMERON, Pashmina Jonathan</creatorcontrib><creatorcontrib>ALI AKBARIAN, Mohammand Sadegh</creatorcontrib><creatorcontrib>SALEH, Fatemehsadat</creatorcontrib><title>PREDICTING BODY MOTION</title><description>For each of a plurality of time steps: receive a reference joint pose of an articulated entity and receiving an indication that another joint of the articulated entity is unobserved or observed. Prompt a motion model using the reference joint pose and a mask token. The model predicts body motion comprising a trajectory of the articulated entity and a pose of a plurality of joints of the articulated entity. The mask token represents the other joint and is temporally adaptable by: in response to receiving an indication that the other joint is unobserved, using information about the reference joint pose and a pose of the other joint from a previous time step; and in response to receiving an indication that the other joint is observed, using information about the reference joint pose and a pose of the other joint from the current time step.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>OPTICAL ELEMENTS, SYSTEMS, OR APPARATUS</subject><subject>OPTICS</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZBALCHJ18XQO8fRzV3Dyd4lU8PUP8fT342FgTUvMKU7lhdLcDMpuriHOHrqpBfnxqcUFicmpeakl8aHBRgZGJkZmJmamFo6GxsSpAgA29iAs</recordid><startdate>20240808</startdate><enddate>20240808</enddate><creator>CAMERON, Pashmina Jonathan</creator><creator>ALI AKBARIAN, Mohammand Sadegh</creator><creator>SALEH, Fatemehsadat</creator><scope>EVB</scope></search><sort><creationdate>20240808</creationdate><title>PREDICTING BODY MOTION</title><author>CAMERON, Pashmina Jonathan ; ALI AKBARIAN, Mohammand Sadegh ; SALEH, Fatemehsadat</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2024264658A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>OPTICAL ELEMENTS, SYSTEMS, OR APPARATUS</topic><topic>OPTICS</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>CAMERON, Pashmina Jonathan</creatorcontrib><creatorcontrib>ALI AKBARIAN, Mohammand Sadegh</creatorcontrib><creatorcontrib>SALEH, Fatemehsadat</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>CAMERON, Pashmina Jonathan</au><au>ALI AKBARIAN, Mohammand Sadegh</au><au>SALEH, Fatemehsadat</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>PREDICTING BODY MOTION</title><date>2024-08-08</date><risdate>2024</risdate><abstract>For each of a plurality of time steps: receive a reference joint pose of an articulated entity and receiving an indication that another joint of the articulated entity is unobserved or observed. Prompt a motion model using the reference joint pose and a mask token. The model predicts body motion comprising a trajectory of the articulated entity and a pose of a plurality of joints of the articulated entity. The mask token represents the other joint and is temporally adaptable by: in response to receiving an indication that the other joint is unobserved, using information about the reference joint pose and a pose of the other joint from a previous time step; and in response to receiving an indication that the other joint is observed, using information about the reference joint pose and a pose of the other joint from the current time step.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US2024264658A1
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
OPTICAL ELEMENTS, SYSTEMS, OR APPARATUS
OPTICS
PHYSICS
title PREDICTING BODY MOTION
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T02%3A18%3A09IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=CAMERON,%20Pashmina%20Jonathan&rft.date=2024-08-08&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2024264658A1%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true