ATTRIBUTING ASPECTS OF GENERATED VISUAL CONTENTS TO TRAINING EXAMPLES
Systems, methods and non-transitory computer readable media for attributing aspects of generated visual contents to training examples are provided. A first visual content generated using a generative model may be received. The generative model may be a result of training a machine learning model usi...
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| 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 | SARID, Nimrod Horesh-Yaniv, Vered FEINSTEIN, Michael ADATO, Yair MOKADY, Ron GUTFLAISH, Eyal |
| description | Systems, methods and non-transitory computer readable media for attributing aspects of generated visual contents to training examples are provided. A first visual content generated using a generative model may be received. The generative model may be a result of training a machine learning model using a plurality of training examples. Properties of an aspect of the first visual content and properties of visual contents associated with the plurality of training examples may be used to attribute the aspect of the first visual content to a subgroup of the plurality of training examples. For each source of the sources associated with the visual contents associated with the training examples of the subgroup, a data-record associated with the source may be updated based on the attribution of the aspect of the first visual content. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2024273865A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2024273865A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2024273865A13</originalsourceid><addsrcrecordid>eNrjZHB1DAkJ8nQKDfH0c1dwDA5wdQ4JVvB3U3B39XMNcgxxdVEI8wwOdfRRcPb3C3H1A0qG-CuEBDl6-oE0uEY4-gb4uAbzMLCmJeYUp_JCaW4GZTfXEGcP3dSC_PjU4oLE5NS81JL40GAjAyMTI3NjCzNTR0Nj4lQBAFudLVI</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>ATTRIBUTING ASPECTS OF GENERATED VISUAL CONTENTS TO TRAINING EXAMPLES</title><source>esp@cenet</source><creator>SARID, Nimrod ; Horesh-Yaniv, Vered ; FEINSTEIN, Michael ; ADATO, Yair ; MOKADY, Ron ; GUTFLAISH, Eyal</creator><creatorcontrib>SARID, Nimrod ; Horesh-Yaniv, Vered ; FEINSTEIN, Michael ; ADATO, Yair ; MOKADY, Ron ; GUTFLAISH, Eyal</creatorcontrib><description>Systems, methods and non-transitory computer readable media for attributing aspects of generated visual contents to training examples are provided. A first visual content generated using a generative model may be received. The generative model may be a result of training a machine learning model using a plurality of training examples. Properties of an aspect of the first visual content and properties of visual contents associated with the plurality of training examples may be used to attribute the aspect of the first visual content to a subgroup of the plurality of training examples. For each source of the sources associated with the visual contents associated with the training examples of the subgroup, a data-record associated with the source may be updated based on the attribution of the aspect of the first visual content.</description><language>eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; 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&date=20240815&DB=EPODOC&CC=US&NR=2024273865A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25563,76418</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240815&DB=EPODOC&CC=US&NR=2024273865A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>SARID, Nimrod</creatorcontrib><creatorcontrib>Horesh-Yaniv, Vered</creatorcontrib><creatorcontrib>FEINSTEIN, Michael</creatorcontrib><creatorcontrib>ADATO, Yair</creatorcontrib><creatorcontrib>MOKADY, Ron</creatorcontrib><creatorcontrib>GUTFLAISH, Eyal</creatorcontrib><title>ATTRIBUTING ASPECTS OF GENERATED VISUAL CONTENTS TO TRAINING EXAMPLES</title><description>Systems, methods and non-transitory computer readable media for attributing aspects of generated visual contents to training examples are provided. A first visual content generated using a generative model may be received. The generative model may be a result of training a machine learning model using a plurality of training examples. Properties of an aspect of the first visual content and properties of visual contents associated with the plurality of training examples may be used to attribute the aspect of the first visual content to a subgroup of the plurality of training examples. For each source of the sources associated with the visual contents associated with the training examples of the subgroup, a data-record associated with the source may be updated based on the attribution of the aspect of the first visual content.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZHB1DAkJ8nQKDfH0c1dwDA5wdQ4JVvB3U3B39XMNcgxxdVEI8wwOdfRRcPb3C3H1A0qG-CuEBDl6-oE0uEY4-gb4uAbzMLCmJeYUp_JCaW4GZTfXEGcP3dSC_PjU4oLE5NS81JL40GAjAyMTI3NjCzNTR0Nj4lQBAFudLVI</recordid><startdate>20240815</startdate><enddate>20240815</enddate><creator>SARID, Nimrod</creator><creator>Horesh-Yaniv, Vered</creator><creator>FEINSTEIN, Michael</creator><creator>ADATO, Yair</creator><creator>MOKADY, Ron</creator><creator>GUTFLAISH, Eyal</creator><scope>EVB</scope></search><sort><creationdate>20240815</creationdate><title>ATTRIBUTING ASPECTS OF GENERATED VISUAL CONTENTS TO TRAINING EXAMPLES</title><author>SARID, Nimrod ; Horesh-Yaniv, Vered ; FEINSTEIN, Michael ; ADATO, Yair ; MOKADY, Ron ; GUTFLAISH, Eyal</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2024273865A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>SARID, Nimrod</creatorcontrib><creatorcontrib>Horesh-Yaniv, Vered</creatorcontrib><creatorcontrib>FEINSTEIN, Michael</creatorcontrib><creatorcontrib>ADATO, Yair</creatorcontrib><creatorcontrib>MOKADY, Ron</creatorcontrib><creatorcontrib>GUTFLAISH, Eyal</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>SARID, Nimrod</au><au>Horesh-Yaniv, Vered</au><au>FEINSTEIN, Michael</au><au>ADATO, Yair</au><au>MOKADY, Ron</au><au>GUTFLAISH, Eyal</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>ATTRIBUTING ASPECTS OF GENERATED VISUAL CONTENTS TO TRAINING EXAMPLES</title><date>2024-08-15</date><risdate>2024</risdate><abstract>Systems, methods and non-transitory computer readable media for attributing aspects of generated visual contents to training examples are provided. A first visual content generated using a generative model may be received. The generative model may be a result of training a machine learning model using a plurality of training examples. Properties of an aspect of the first visual content and properties of visual contents associated with the plurality of training examples may be used to attribute the aspect of the first visual content to a subgroup of the plurality of training examples. For each source of the sources associated with the visual contents associated with the training examples of the subgroup, a data-record associated with the source may be updated based on the attribution of the aspect of the first visual content.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US2024273865A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING PHYSICS |
| title | ATTRIBUTING ASPECTS OF GENERATED VISUAL CONTENTS TO TRAINING EXAMPLES |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-09T08%3A17%3A03IST&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=SARID,%20Nimrod&rft.date=2024-08-15&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2024273865A1%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 |