{"id":"https://openalex.org/W4415055103","doi":"https://doi.org/10.1109/wacv61042.2026.00274","title":"UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning","display_name":"UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4415055103","doi":"https://doi.org/10.1109/wacv61042.2026.00274"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00274","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.06165","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029085597","display_name":"Huy Le","orcid":"https://orcid.org/0000-0002-4811-3915"},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Huy Le","raw_affiliation_strings":["FPT Software AI Center,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FPT Software AI Center,Vietnam","institution_ids":["https://openalex.org/I109689652"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114168283","display_name":"Nhat Chung","orcid":null},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Nhat Chung","raw_affiliation_strings":["FPT Software AI Center,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FPT Software AI Center,Vietnam","institution_ids":["https://openalex.org/I109689652"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016799625","display_name":"Tung Kieu","orcid":"https://orcid.org/0000-0002-7696-1444"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Tung Kieu","raw_affiliation_strings":["Aalborg University,Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102413036","display_name":"Jingkang Yang","orcid":"https://orcid.org/0000-0002-2923-3137"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jingkang Yang","raw_affiliation_strings":["Nanyang Technological University,S-Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,S-Lab,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102698991","display_name":"Ngan Le","orcid":null},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ngan Le","raw_affiliation_strings":["University of Arkansas,AICV Lab,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Arkansas,AICV Lab,USA","institution_ids":["https://openalex.org/I78715868"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"2797","last_page":"2807"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9966999888420105,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9948999881744385,"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/generalization","display_name":"Generalization","score":0.5302000045776367},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5206000208854675},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5123000144958496},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5077999830245972},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4855000078678131},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.460099995136261},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.4537000060081482},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.37380000948905945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7918000221252441},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5861999988555908},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5302000045776367},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5206000208854675},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5123000144958496},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5077999830245972},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4855000078678131},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.460099995136261},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.4537000060081482},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4219000041484833},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.37380000948905945},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.34689998626708984},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.31690001487731934},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C2777742833","wikidata":"https://www.wikidata.org/wiki/Q1964083","display_name":"Reciprocal","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/wacv61042.2026.00274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00274","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.06165","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.06165","pdf_url":"https://arxiv.org/pdf/2509.06165","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:doi:10.48550/arxiv.2509.06165","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:pure.atira.dk:publications/f3edd43c-d3f1-4d6c-a33d-190cdd744bd6","is_oa":false,"landing_page_url":"https://vbn.aau.dk/da/publications/f3edd43c-d3f1-4d6c-a33d-190cdd744bd6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Le, H, Chung, N, Kieu, T, Yang, J & Le, N 2025 'UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning'.","raw_type":"workingPaper"},{"id":"doi:10.48550/arxiv.2509.06165","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.06165","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.06165","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.06165","pdf_url":"https://arxiv.org/pdf/2509.06165","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0],"Scene":[1],"Graph":[2],"Generation":[3],"(VidSGG)":[4],"aims":[5],"to":[6,67,135],"represent":[7],"dynamic":[8,128],"visual":[9,81,95],"content":[10],"by":[11],"detecting":[12],"objects":[13],"and":[14,38,71,99,150],"modeling":[15],"their":[16],"temporal":[17,105,110],"interactions":[18,141],"as":[19],"structured":[20],"graphs.":[21],"Prior":[22],"studies":[23],"typically":[24],"target":[25],"either":[26],"coarse-grained":[27],"box-level":[28,149],"or":[29],"fine-grained":[30],"panoptic":[31],"pixel-level":[32,151],"VidSGG,":[33],"often":[34],"requiring":[35],"task-specific":[36,69],"architectures":[37],"multi-stage":[39],"training":[40],"pipelines.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,107],"present":[46],"UNO":[47,64,86,146,157],"(UNified":[48],"Object-centric":[49],"VidSGG),":[50],"a":[51,127,172],"single-stage,":[52],"unified":[53],"framework":[54],"that":[55,93,156],"jointly":[56],"addresses":[57],"both":[58,164],"tasks":[59,165],"within":[60],"an":[61,88],"end-to-end":[62],"architecture.":[63],"is":[65,87],"designed":[66],"minimize":[68],"modifications":[70],"maximize":[72],"parameter":[73],"sharing,":[74],"enabling":[75],"generalization":[76],"across":[77,118,163],"different":[78],"levels":[79],"of":[80,85],"granularity.":[82],"The":[83],"core":[84],"extended":[89],"slot":[90],"attention":[91],"mechanism":[92],"decomposes":[94],"features":[96],"into":[97],"object":[98,109,116,137],"relation":[100,133],"slots.":[101],"To":[102],"ensure":[103],"robust":[104],"modeling,":[106],"introduce":[108],"consistency":[111],"learning,":[112],"which":[113],"enforces":[114],"consistent":[115],"representations":[117],"frames":[119],"without":[120],"relying":[121],"on":[122,147],"explicit":[123],"tracking":[124],"modules.":[125],"Additionally,":[126],"triplet":[129],"prediction":[130],"module":[131],"links":[132],"slots":[134],"corresponding":[136],"pairs,":[138],"capturing":[139],"evolving":[140],"over":[142],"time.":[143],"We":[144],"evaluate":[145],"standard":[148],"VidSGG":[152],"benchmarks.":[153],"Results":[154],"demonstrate":[155],"not":[158],"only":[159],"achieves":[160],"competitive":[161],"performance":[162],"but":[166],"also":[167],"offers":[168],"improved":[169],"efficiency":[170],"through":[171],"unified,":[173],"object-centric":[174],"design.":[175]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-11T00:00:00"}