Video search segmentation
Embodiments are directed to video segmentation based on a query. Initially, a first segmentation such as a default segmentation is displayed (e.g., as interactive tiles in a finder interface, as a video timeline in an editor interface), and the default segmentation is re-segmented in response to a u...
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 | Popović, Jovan Shin, Hijung Dontcheva, Lubomira Fraser, Cristin Ailidh Brandt, Joel Richard Agarwala, Aseem |
| description | Embodiments are directed to video segmentation based on a query. Initially, a first segmentation such as a default segmentation is displayed (e.g., as interactive tiles in a finder interface, as a video timeline in an editor interface), and the default segmentation is re-segmented in response to a user query. The query can take the form of a keyword and one or more selected facets in a category of detected features. Keywords are searched for detected transcript words, detected object or action tags, or detected audio event tags that match the keywords. Selected facets are searched for detected instances of the selected facets. Each video segment that matches the query is re-segmented by solving a shortest path problem through a graph that models different segmentation options. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US11810358B2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US11810358B2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US11810358B23</originalsourceid><addsrcrecordid>eNrjZJAMy0xJzVcoTk0sSs4AUum5qXkliSWZ-Xk8DKxpiTnFqbxQmptB0c01xNlDN7UgPz61uCAxOTUvtSQ-NNjQ0MLQwNjUwsnImBg1ACr4IuU</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Video search segmentation</title><source>esp@cenet</source><creator>Popović, Jovan ; Shin, Hijung ; Dontcheva, Lubomira ; Fraser, Cristin Ailidh ; Brandt, Joel Richard ; Agarwala, Aseem</creator><creatorcontrib>Popović, Jovan ; Shin, Hijung ; Dontcheva, Lubomira ; Fraser, Cristin Ailidh ; Brandt, Joel Richard ; Agarwala, Aseem</creatorcontrib><description>Embodiments are directed to video segmentation based on a query. Initially, a first segmentation such as a default segmentation is displayed (e.g., as interactive tiles in a finder interface, as a video timeline in an editor interface), and the default segmentation is re-segmented in response to a user query. The query can take the form of a keyword and one or more selected facets in a category of detected features. Keywords are searched for detected transcript words, detected object or action tags, or detected audio event tags that match the keywords. Selected facets are searched for detected instances of the selected facets. Each video segment that matches the query is re-segmented by solving a shortest path problem through a graph that models different segmentation options.</description><language>eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; INFORMATION STORAGE ; INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORDCARRIER AND TRANSDUCER ; PHYSICS</subject><creationdate>2023</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=20231107&DB=EPODOC&CC=US&NR=11810358B2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25544,76293</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20231107&DB=EPODOC&CC=US&NR=11810358B2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Popović, Jovan</creatorcontrib><creatorcontrib>Shin, Hijung</creatorcontrib><creatorcontrib>Dontcheva, Lubomira</creatorcontrib><creatorcontrib>Fraser, Cristin Ailidh</creatorcontrib><creatorcontrib>Brandt, Joel Richard</creatorcontrib><creatorcontrib>Agarwala, Aseem</creatorcontrib><title>Video search segmentation</title><description>Embodiments are directed to video segmentation based on a query. Initially, a first segmentation such as a default segmentation is displayed (e.g., as interactive tiles in a finder interface, as a video timeline in an editor interface), and the default segmentation is re-segmented in response to a user query. The query can take the form of a keyword and one or more selected facets in a category of detected features. Keywords are searched for detected transcript words, detected object or action tags, or detected audio event tags that match the keywords. Selected facets are searched for detected instances of the selected facets. Each video segment that matches the query is re-segmented by solving a shortest path problem through a graph that models different segmentation options.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>INFORMATION STORAGE</subject><subject>INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORDCARRIER AND TRANSDUCER</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZJAMy0xJzVcoTk0sSs4AUum5qXkliSWZ-Xk8DKxpiTnFqbxQmptB0c01xNlDN7UgPz61uCAxOTUvtSQ-NNjQ0MLQwNjUwsnImBg1ACr4IuU</recordid><startdate>20231107</startdate><enddate>20231107</enddate><creator>Popović, Jovan</creator><creator>Shin, Hijung</creator><creator>Dontcheva, Lubomira</creator><creator>Fraser, Cristin Ailidh</creator><creator>Brandt, Joel Richard</creator><creator>Agarwala, Aseem</creator><scope>EVB</scope></search><sort><creationdate>20231107</creationdate><title>Video search segmentation</title><author>Popović, Jovan ; Shin, Hijung ; Dontcheva, Lubomira ; Fraser, Cristin Ailidh ; Brandt, Joel Richard ; Agarwala, Aseem</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US11810358B23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>INFORMATION STORAGE</topic><topic>INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORDCARRIER AND TRANSDUCER</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>Popović, Jovan</creatorcontrib><creatorcontrib>Shin, Hijung</creatorcontrib><creatorcontrib>Dontcheva, Lubomira</creatorcontrib><creatorcontrib>Fraser, Cristin Ailidh</creatorcontrib><creatorcontrib>Brandt, Joel Richard</creatorcontrib><creatorcontrib>Agarwala, Aseem</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Popović, Jovan</au><au>Shin, Hijung</au><au>Dontcheva, Lubomira</au><au>Fraser, Cristin Ailidh</au><au>Brandt, Joel Richard</au><au>Agarwala, Aseem</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Video search segmentation</title><date>2023-11-07</date><risdate>2023</risdate><abstract>Embodiments are directed to video segmentation based on a query. Initially, a first segmentation such as a default segmentation is displayed (e.g., as interactive tiles in a finder interface, as a video timeline in an editor interface), and the default segmentation is re-segmented in response to a user query. The query can take the form of a keyword and one or more selected facets in a category of detected features. Keywords are searched for detected transcript words, detected object or action tags, or detected audio event tags that match the keywords. Selected facets are searched for detected instances of the selected facets. Each video segment that matches the query is re-segmented by solving a shortest path problem through a graph that models different segmentation options.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US11810358B2 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING INFORMATION STORAGE INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORDCARRIER AND TRANSDUCER PHYSICS |
| title | Video search segmentation |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-27T12%3A00%3A12IST&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=Popovi%C4%87,%20Jovan&rft.date=2023-11-07&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS11810358B2%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 |