{"id":"https://openalex.org/W7166849490","doi":"https://doi.org/10.18653/v1/2026.acl-long.172","title":"Bringing Real-World Relations into Video Generation with Graph-Structured Knowledge","display_name":"Bringing Real-World Relations into Video Generation with Graph-Structured Knowledge","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166849490","doi":"https://doi.org/10.18653/v1/2026.acl-long.172"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.172","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.172","pdf_url":"https://aclanthology.org/2026.acl-long.172.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.172.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058234906","display_name":"Joonhyung Park","orcid":"https://orcid.org/0000-0003-4662-0099"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joonhyung Park","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040424261","display_name":"Jaeyun Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaeyun Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139739947","display_name":"Sihwan Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sihwan Park","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139739042","display_name":"Eunho Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eunho Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86247372,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3756","last_page":"3771"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8479999899864197,"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":0.8479999899864197,"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":0.051600001752376556,"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":0.019099999219179153,"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/relation","display_name":"Relation (database)","score":0.2944999933242798},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.27559998631477356},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.262800008058548},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2475000023841858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5673999786376953},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.30979999899864197},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.29100000858306885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.26969999074935913},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2524000108242035},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2475000023841858}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.172","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.172","pdf_url":"https://aclanthology.org/2026.acl-long.172.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.172","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.172","pdf_url":"https://aclanthology.org/2026.acl-long.172.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2759505043","display_name":null,"funder_award_id":"RS-202400457882","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G2906058445","display_name":null,"funder_award_id":"2022-0-00713","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G3736587842","display_name":null,"funder_award_id":"RS-2019-II190075","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G3812690899","display_name":null,"funder_award_id":"RS-2023","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4468082379","display_name":null,"funder_award_id":"RS-2019-II190075","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G5704809196","display_name":null,"funder_award_id":"RS-2024-00457882","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G7136478344","display_name":null,"funder_award_id":"RS-2023-00209060","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G7327789038","display_name":null,"funder_award_id":"N10250156","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320324161","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166849490.pdf","grobid_xml":"https://content.openalex.org/works/W7166849490.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"proprietary":[1],"video":[2,40,75,88],"generation":[3,82,107],"models":[4,78],"have":[5],"demonstrated":[6],"remarkable":[7],"proficiency":[8],"in":[9,157],"synthesizing":[10],"highly":[11],"realistic":[12],"videos":[13],"from":[14],"textual":[15],"instructions.Most":[16],"open-source":[17],"text-tovideo":[18],"models,":[19],"however,":[20],"still":[21],"struggle":[22],"to":[23,42,79,93,124],"accurately":[24],"simulate":[25],"real-world":[26,155],"physics":[27],"and":[28,37,55,83,99,150],"dynamic":[29],"entity":[30,95],"interactions.Existing":[31],"approaches":[32],"rely":[33],"on":[34],"scaling":[35],"laws":[36],"large-scale,":[38],"high-quality":[39],"datasets":[41],"implicitly":[43],"learn":[44],"physical":[45],"dynamics,":[46,98],"yet":[47],"this":[48],"paradigm":[49],"is":[50],"constrained":[51],"by":[52,62,127],"prohibitive":[53],"costs":[54],"the":[56,106,133,151],"burdensome":[57],"demands":[58],"of":[59,154],"data":[60],"curation.Motivated":[61],"this,":[63],"we":[64,112],"propose":[65],"a":[66,118],"novel":[67],"framework":[68,86],"that":[69,121,143],"integrates":[70],"graph-structured":[71],"temporal":[72,97],"knowledge":[73,146],"into":[74],"latent":[76],"diffusion":[77],"enhance":[80],"compositional":[81],"interaction":[84],"fidelity.Our":[85],"constructs":[87],"scene":[89,101],"graphs":[90,126],"specifically":[91],"designed":[92],"capture":[94],"relationships,":[96],"global":[100],"context.These":[102],"graphstructured":[103,145],"representations":[104],"guide":[105],"process":[108],"through":[109],"cross-attention":[110],"mechanisms.Additionally,":[111],"introduce":[113],"Graph-Aligned":[114],"Denoising":[115],"Loss":[116],"(GADL),":[117],"training":[119],"objective":[120],"ensures":[122],"adherence":[123],"conditioned":[125],"incorporating":[128,144],"node":[129],"modification":[130],"tasks":[131],"within":[132],"denoising":[134],"process,":[135],"leveraging":[136],"synchronized":[137],"edited":[138],"video-graph":[139],"pairs.Comprehensive":[140],"evaluations":[141],"demonstrate":[142],"significantly":[147],"enhances":[148],"compositionality":[149],"accurate":[152],"portrayal":[153],"interactions":[156],"generated":[158],"videos.":[159]},"counts_by_year":[],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2026-07-02T00:00:00"}