{"id":"https://openalex.org/W7130612110","doi":"https://doi.org/10.1109/ictc66702.2025.11388404","title":"Temporal Prompting with Vision-Language Models for Consistent Video Scene Graph Generation","display_name":"Temporal Prompting with Vision-Language Models for Consistent Video Scene Graph Generation","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W7130612110","doi":"https://doi.org/10.1109/ictc66702.2025.11388404"},"language":null,"primary_location":{"id":"doi:10.1109/ictc66702.2025.11388404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11388404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100747327","display_name":"Dongjin Lee","orcid":"https://orcid.org/0000-0002-7575-868X"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dohyeong Lee","raw_affiliation_strings":["Electronics and Telecommunications Research Institute,Defense & Safety Convergence Research Division,Daejeon,Korea,34129"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute,Defense & Safety Convergence Research Division,Daejeon,Korea,34129","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039702958","display_name":"Choulsoo Jang","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Choulsoo Jang","raw_affiliation_strings":["Electronics and Telecommunications Research Institute,Defense & Safety Convergence Research Division,Daejeon,Korea,34129"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute,Defense & Safety Convergence Research Division,Daejeon,Korea,34129","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126428535","display_name":"Sang-Kyu Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sang-Kyu Lim","raw_affiliation_strings":["Electronics and Telecommunications Research Institute,Defense & Safety Convergence Research Division,Daejeon,Korea,34129"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute,Defense & Safety Convergence Research Division,Daejeon,Korea,34129","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080108695","display_name":"Chang-Eun Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chang-Eun Lee","raw_affiliation_strings":["Electronics and Telecommunications Research Institute,Defense & Safety Convergence Research Division,Daejeon,Korea,34129"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute,Defense & Safety Convergence Research Division,Daejeon,Korea,34129","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I142401562"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9677000045776367,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9677000045776367,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.01600000075995922,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.0032999999821186066,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.48829999566078186},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.48809999227523804},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.47279998660087585},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4659999907016754},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45249998569488525},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4034999907016754},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.385699987411499},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.3817000091075897}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7695000171661377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6366999745368958},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.48829999566078186},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48809999227523804},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.47279998660087585},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4659999907016754},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45249998569488525},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4034999907016754},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3817000091075897},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36309999227523804},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.32350000739097595},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2948000133037567},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc66702.2025.11388404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11388404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334874","display_name":"Defense Acquisition Program Administration","ror":"https://ror.org/04bjg9m96"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2277195237","https://openalex.org/W2603203130","https://openalex.org/W2765137706","https://openalex.org/W2951323451","https://openalex.org/W3034679267","https://openalex.org/W3173859428","https://openalex.org/W3186621246","https://openalex.org/W3193902142","https://openalex.org/W3198377975","https://openalex.org/W4200498145","https://openalex.org/W4313026212","https://openalex.org/W4404612908"],"related_works":[],"abstract_inverted_index":{"Video":[0],"scene":[1,56,131,169],"graphs":[2],"capture":[3],"objects,":[4],"represented":[5],"as":[6,36],"nodes":[7],"and":[8,67,76,90,104,106,109,120,150],"their":[9,68],"temporal":[10,46,63,79,82,142],"relationships,":[11,69],"providing":[12],"a":[13,45,135],"structured":[14],"representation":[15],"for":[16,49,165],"video":[17,55,130,137,168],"understanding.":[18],"However,":[19],"constructing":[20],"large-scale":[21],"annotated":[22,177],"datasets":[23],"is":[24,33],"challenging":[25],"in":[26,129,173],"specialized":[27],"domains":[28,174],"where":[29],"real-world":[30],"data":[31],"collection":[32],"infeasible,":[34],"such":[35],"the":[37,62,71,77,113,125,162],"military":[38],"domain.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43],"propose":[44],"prompting":[47,83,143],"framework":[48,60,99,114],"vision-language":[50],"models":[51],"to":[52,93,123,156],"generate":[53],"consistent":[54,95],"graphs.":[57,132],"Specifically,":[58],"our":[59,141],"ensures":[61],"consistency":[64,126],"of":[65,73,127],"objects":[66],"preserving":[70],"meaning":[72],"each":[74],"frame":[75],"overall":[78,153],"context.":[80],"Our":[81],"strategy":[84],"leverages":[85],"previous-frame":[86],"tracking,":[87],"object":[88],"states,":[89],"relational":[91,96],"context":[92],"enable":[94],"annotations.":[97],"The":[98],"comprises":[100],"two":[101,116],"steps:":[102],"detection":[103],"alignment,":[105],"relation":[107],"estimation":[108],"alignment.":[110],"We":[111],"evaluate":[112],"using":[115],"metrics,":[117],"frame-level":[118],"recall":[119],"continuity":[121],"recall,":[122],"assess":[124],"relationships":[128],"Experiments":[133],"on":[134],"public":[136],"dataset":[138],"demonstrate":[139],"that":[140],"approach":[144],"yields":[145],"more":[146],"continuous":[147],"relationship":[148],"predictions":[149],"achieves":[151],"better":[152],"performance":[154],"compared":[155],"baseline":[157],"prompting.":[158],"These":[159],"results":[160],"highlight":[161],"framework\u2019s":[163],"potential":[164],"producing":[166],"training-ready":[167],"graph":[170],"datasets,":[171],"particularly":[172],"with":[175],"scarce":[176],"data.":[178]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-20T00:00:00"}