{"id":"https://openalex.org/W4390872535","doi":"https://doi.org/10.1109/iccv51070.2023.00641","title":"Unified Visual Relationship Detection with Vision and Language Models","display_name":"Unified Visual Relationship Detection with Vision and Language Models","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4390872535","doi":"https://doi.org/10.1109/iccv51070.2023.00641"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51070.2023.00641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51070.2023.00641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","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/A5101850043","display_name":"L. Zhao","orcid":"https://orcid.org/0000-0001-8921-8564"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Long Zhao","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008194726","display_name":"Liangzhe Yuan","orcid":"https://orcid.org/0000-0001-9206-1908"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liangzhe Yuan","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017319429","display_name":"Boqing Gong","orcid":"https://orcid.org/0000-0003-3915-5977"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boqing Gong","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041864624","display_name":"Yin Cui","orcid":"https://orcid.org/0000-0003-0070-5118"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yin Cui","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048629871","display_name":"Florian Schroff","orcid":"https://orcid.org/0000-0003-0570-8967"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Schroff","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418319","display_name":"Ming\u2013Hsuan Yang","orcid":"https://orcid.org/0000-0003-4848-2304"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming-Hsuan Yang","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030402556","display_name":"Hartwig Adam","orcid":"https://orcid.org/0000-0003-1258-4341"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hartwig Adam","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418161","display_name":"Ting Liu","orcid":"https://orcid.org/0000-0003-0749-064X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ting Liu","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3473,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.83670146,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6939","last_page":"6950"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9972000122070312,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9968000054359436,"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/computer-science","display_name":"Computer science","score":0.8166517019271851},{"id":"https://openalex.org/keywords/unification","display_name":"Unification","score":0.7162463068962097},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6120465397834778},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.605288565158844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.597999095916748},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5509082078933716},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.529360830783844},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4465769827365875},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42848819494247437},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4114699363708496},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3890005946159363},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3134618401527405},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.18835562467575073},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.11581411957740784},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09615227580070496}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8166517019271851},{"id":"https://openalex.org/C96146094","wikidata":"https://www.wikidata.org/wiki/Q609057","display_name":"Unification","level":2,"score":0.7162463068962097},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6120465397834778},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.605288565158844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.597999095916748},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5509082078933716},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.529360830783844},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4465769827365875},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42848819494247437},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4114699363708496},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3890005946159363},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3134618401527405},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.18835562467575073},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.11581411957740784},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09615227580070496},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv51070.2023.00641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51070.2023.00641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":102,"referenced_works":["https://openalex.org/W1551928752","https://openalex.org/W1614298861","https://openalex.org/W1861492603","https://openalex.org/W2222512263","https://openalex.org/W2277195237","https://openalex.org/W2479423890","https://openalex.org/W2559085405","https://openalex.org/W2579549467","https://openalex.org/W2888096830","https://openalex.org/W2896457183","https://openalex.org/W2939059980","https://openalex.org/W2950496566","https://openalex.org/W2955639361","https://openalex.org/W2962766617","https://openalex.org/W2962785943","https://openalex.org/W2963097937","https://openalex.org/W2963351448","https://openalex.org/W2963518342","https://openalex.org/W2963536419","https://openalex.org/W2963938081","https://openalex.org/W2964225075","https://openalex.org/W2978956737","https://openalex.org/W2983943451","https://openalex.org/W3009811369","https://openalex.org/W3034538190","https://openalex.org/W3034895839","https://openalex.org/W3034934229","https://openalex.org/W3034951775","https://openalex.org/W3035017890","https://openalex.org/W3035086574","https://openalex.org/W3035598501","https://openalex.org/W3081167590","https://openalex.org/W3081642947","https://openalex.org/W3090476579","https://openalex.org/W3095753865","https://openalex.org/W3097802466","https://openalex.org/W3102452576","https://openalex.org/W3106121867","https://openalex.org/W3106328333","https://openalex.org/W3106827427","https://openalex.org/W3106988096","https://openalex.org/W3107081247","https://openalex.org/W3108864070","https://openalex.org/W3109813419","https://openalex.org/W3138006590","https://openalex.org/W3168279596","https://openalex.org/W3168488421","https://openalex.org/W3171169846","https://openalex.org/W3173018607","https://openalex.org/W3173859428","https://openalex.org/W3174164794","https://openalex.org/W3174480456","https://openalex.org/W3181556077","https://openalex.org/W3181762391","https://openalex.org/W3184735396","https://openalex.org/W3191092153","https://openalex.org/W3196335607","https://openalex.org/W3204250462","https://openalex.org/W3205051885","https://openalex.org/W3212153990","https://openalex.org/W3213454282","https://openalex.org/W4214693531","https://openalex.org/W4225323055","https://openalex.org/W4226058394","https://openalex.org/W4297632532","https://openalex.org/W4312456860","https://openalex.org/W4312538795","https://openalex.org/W4312563428","https://openalex.org/W4312613394","https://openalex.org/W4312735840","https://openalex.org/W4312773012","https://openalex.org/W4312956471","https://openalex.org/W4312960102","https://openalex.org/W4313037583","https://openalex.org/W4313155487","https://openalex.org/W4366352717","https://openalex.org/W4385567175","https://openalex.org/W6631190155","https://openalex.org/W6632922691","https://openalex.org/W6636510571","https://openalex.org/W6726497184","https://openalex.org/W6754152559","https://openalex.org/W6755207826","https://openalex.org/W6767216089","https://openalex.org/W6769627184","https://openalex.org/W6784094891","https://openalex.org/W6784333009","https://openalex.org/W6785527955","https://openalex.org/W6790019176","https://openalex.org/W6790830454","https://openalex.org/W6791353385","https://openalex.org/W6792148081","https://openalex.org/W6798805250","https://openalex.org/W6799822930","https://openalex.org/W6802347785","https://openalex.org/W6802517928","https://openalex.org/W6810334672","https://openalex.org/W6810419797","https://openalex.org/W6811072154","https://openalex.org/W6839632867","https://openalex.org/W6842585177","https://openalex.org/W6843484045"],"related_works":["https://openalex.org/W2367630557","https://openalex.org/W101666983","https://openalex.org/W2183792531","https://openalex.org/W2595286499","https://openalex.org/W2794344379","https://openalex.org/W2489197555","https://openalex.org/W2471908688","https://openalex.org/W1845283042","https://openalex.org/W3171337446","https://openalex.org/W2884423176"],"abstract_inverted_index":{"This":[0],"work":[1],"focuses":[2],"on":[3,116,135,180],"training":[4,105],"a":[5,57],"single":[6],"visual":[7,37,42,111],"relationship":[8,38,112],"detector":[9,143,154],"predicting":[10],"over":[11],"the":[12,98,102,125,138,171],"union":[13],"of":[14,48,104,128],"label":[15],"spaces":[16],"from":[17],"multiple":[18],"datasets.":[19,113],"Merging":[20],"labels":[21],"spanning":[22],"different":[23],"datasets":[24],"could":[25],"be":[26,86,176],"challenging":[27],"due":[28],"to":[29,85,88,100],"inconsistent":[30],"taxonomies.":[31],"The":[32],"issue":[33],"is":[34],"exacerbated":[35],"in":[36,161],"detection":[39,109,120],"when":[40,167],"second-order":[41],"semantics":[43],"are":[44,83],"introduced":[45],"between":[46],"pairs":[47],"objects.":[49],"To":[50],"address":[51],"this":[52],"challenge,":[53],"we":[54,149,168],"propose":[55],"UniVRD,":[56],"novel":[58],"bottom-up":[59,95,141],"method":[60],"for":[61,91],"Unified":[62],"Visual":[63],"Relationship":[64],"Detection":[65],"by":[66,144],"leveraging":[67],"vision":[68],"and":[69,77,110,121,163],"language":[70],"models":[71,160],"(VLMs).":[72],"VLMs":[73],"provide":[74],"well-aligned":[75],"image":[76],"text":[78],"embeddings,":[79],"where":[80],"similar":[81],"relationships":[82],"optimized":[84],"close":[87],"each":[89],"other":[90],"semantic":[92],"unification.":[93],"Our":[94,173],"design":[96],"enables":[97],"model":[99],"enjoy":[101],"benefit":[103],"with":[106],"both":[107,117],"object":[108],"Empirical":[114],"results":[115],"human-object":[118],"interaction":[119],"scene-graph":[122],"generation":[123],"demonstrate":[124],"competitive":[126],"performance":[127],"our":[129,152],"model.":[130,172],"UniVRD":[131],"achieves":[132,164],"38.07":[133],"mAP":[134],"HICO-DET,":[136],"outperforming":[137],"current":[139],"best":[140],"HOI":[142],"14.26":[145],"mAP.":[146],"More":[147],"importantly,":[148],"show":[150],"that":[151],"unified":[153],"performs":[155],"as":[156,158],"well":[157],"dataset-specific":[159],"mAP,":[162],"further":[165],"improvements":[166],"scale":[169],"up":[170],"code":[174],"will":[175],"made":[177],"publicly":[178],"available":[179],"GitHub":[181],"<sup":[182],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[183],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[184],".":[185]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}