{"id":"https://openalex.org/W7138324868","doi":"https://doi.org/10.1609/aaai.v40i16.38370","title":"Seeing and Knowing in the Wild: Open-domain Visual Entity Recognition with Large-scale Knowledge Graphs via Contrastive Learning","display_name":"Seeing and Knowing in the Wild: Open-domain Visual Entity Recognition with Large-scale Knowledge Graphs via Contrastive Learning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138324868","doi":"https://doi.org/10.1609/aaai.v40i16.38370"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i16.38370","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38370","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i16.38370","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129663167","display_name":"Hongkuan Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I2802101015","display_name":"Robert Bosch Stiftung","ror":"https://ror.org/012kqkf58","country_code":"DE","type":"funder","lineage":["https://openalex.org/I2802101015"]},{"id":"https://openalex.org/I2802768257","display_name":"Robert Bosch Hospital","ror":"https://ror.org/034nkkr84","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I2802101015","https://openalex.org/I2802768257","https://openalex.org/I4403386655"]},{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Hongkuan Zhou","raw_affiliation_strings":["Robert Bosch GmbH\nUniversity of Stuttgart"],"affiliations":[{"raw_affiliation_string":"Robert Bosch GmbH\nUniversity of Stuttgart","institution_ids":["https://openalex.org/I2802768257","https://openalex.org/I889804353","https://openalex.org/I2802101015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031926202","display_name":"Lavdim Halilaj","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145457","display_name":"Robert Bosch (Taiwan)","ror":"https://ror.org/046as2g47","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210145457","https://openalex.org/I889804353"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Lavdim Halilaj","raw_affiliation_strings":["Robert Bosch GmbH"],"affiliations":[{"raw_affiliation_string":"Robert Bosch GmbH","institution_ids":["https://openalex.org/I4210145457"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065068289","display_name":"Sebastian Monka","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145457","display_name":"Robert Bosch (Taiwan)","ror":"https://ror.org/046as2g47","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210145457","https://openalex.org/I889804353"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Sebastian Monka","raw_affiliation_strings":["Robert Bosch GmbH"],"affiliations":[{"raw_affiliation_string":"Robert Bosch GmbH","institution_ids":["https://openalex.org/I4210145457"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129730667","display_name":"Stefan Schmid","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145457","display_name":"Robert Bosch (Taiwan)","ror":"https://ror.org/046as2g47","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210145457","https://openalex.org/I889804353"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Stefan Schmid","raw_affiliation_strings":["Robert Bosch GmbH"],"affiliations":[{"raw_affiliation_string":"Robert Bosch GmbH","institution_ids":["https://openalex.org/I4210145457"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031378587","display_name":"Yuqicheng Zhu","orcid":"https://orcid.org/0000-0001-5845-5401"},"institutions":[{"id":"https://openalex.org/I2802101015","display_name":"Robert Bosch Stiftung","ror":"https://ror.org/012kqkf58","country_code":"DE","type":"funder","lineage":["https://openalex.org/I2802101015"]},{"id":"https://openalex.org/I2802768257","display_name":"Robert Bosch Hospital","ror":"https://ror.org/034nkkr84","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I2802101015","https://openalex.org/I2802768257","https://openalex.org/I4403386655"]},{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yuqicheng Zhu","raw_affiliation_strings":["Robert Bosch GmbH\nUniversity of Stuttgart"],"affiliations":[{"raw_affiliation_string":"Robert Bosch GmbH\nUniversity of Stuttgart","institution_ids":["https://openalex.org/I2802768257","https://openalex.org/I889804353","https://openalex.org/I2802101015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006740330","display_name":"Jingcheng Wu","orcid":"https://orcid.org/0009-0002-4279-3355"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jingcheng Wu","raw_affiliation_strings":["University of Stuttgart"],"affiliations":[{"raw_affiliation_string":"University of Stuttgart","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120034744","display_name":"Nadeem Nazer","orcid":null},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nadeem Nazer","raw_affiliation_strings":["Robert Bosch GmbH\nOtto-von-Guericke-University Magdeburg"],"affiliations":[{"raw_affiliation_string":"Robert Bosch GmbH\nOtto-von-Guericke-University Magdeburg","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062807811","display_name":"Steffen Staab","orcid":"https://orcid.org/0000-0002-0780-4154"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]},{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"Steffen Staab","raw_affiliation_strings":["University of Stuttgart\nUniversity of Southampton"],"affiliations":[{"raw_affiliation_string":"University of Stuttgart\nUniversity of Southampton","institution_ids":["https://openalex.org/I100066346","https://openalex.org/I43439940"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5129663167"],"corresponding_institution_ids":["https://openalex.org/I2802101015","https://openalex.org/I2802768257","https://openalex.org/I889804353"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.53800857,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"16","first_page":"13638","last_page":"13646"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.536899983882904,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.536899983882904,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.287200003862381,"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":0.08839999884366989,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.6450999975204468},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.574999988079071},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5612000226974487},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5546000003814697},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4410000145435333},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.3903999924659729},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.38040000200271606},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.2980000078678131},{"id":"https://openalex.org/keywords/statistical-relational-learning","display_name":"Statistical relational learning","score":0.2946000099182129}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8034999966621399},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.711899995803833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6488000154495239},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.6450999975204468},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.574999988079071},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5612000226974487},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5546000003814697},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4410000145435333},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.329800009727478},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.2980000078678131},{"id":"https://openalex.org/C177877439","wikidata":"https://www.wikidata.org/wiki/Q7604413","display_name":"Statistical relational learning","level":3,"score":0.2946000099182129},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C2986420190","wikidata":"https://www.wikidata.org/wiki/Q39045939","display_name":"Semantic space","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2721000015735626},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2671000063419342},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i16.38370","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38370","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i16.38370","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38370","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Open-domain":[0],"visual":[1,64,100,134],"entity":[2,111,121],"recognition":[3,135],"aims":[4],"to":[5,13,60,104,118,175],"identify":[6],"and":[7,16,49,66,84,101,115,151,160],"link":[8],"entities":[9,44,171],"depicted":[10],"in":[11,26],"images":[12,83],"a":[14,74,88,105,131],"vast":[15],"evolving":[17],"set":[18],"of":[19],"real-world":[20],"concepts,":[21],"such":[22],"as":[23,140],"those":[24],"found":[25],"Wikidata.":[27,97],"Unlike":[28],"conventional":[29],"classification":[30],"tasks":[31],"with":[32,137],"fixed":[33],"label":[34,142],"sets,":[35],"it":[36],"operates":[37],"under":[38],"open-set":[39],"conditions,":[40],"where":[41],"most":[42],"target":[43],"are":[45],"unseen":[46,161,170],"during":[47],"training":[48],"exhibit":[50],"long-tail":[51],"distributions.":[52],"This":[53],"makes":[54],"the":[55,67,108,128,141,167,176],"task":[56],"inherently":[57],"challenging":[58],"due":[59],"limited":[61],"supervision,":[62],"high":[63],"ambiguity,":[65],"need":[68],"for":[69,158],"semantic":[70,90],"disambiguation.":[71],"We":[72,123],"propose":[73],"Knowledge-guided":[75],"Contrastive":[76],"Learning":[77],"(KnowCoL)":[78],"framework":[79],"that":[80,147],"combines":[81],"both":[82],"text":[85],"descriptions":[86],"into":[87],"shared":[89],"space":[91],"grounded":[92],"by":[93,172],"structured":[94,152],"information":[95],"from":[96],"By":[98],"abstracting":[99],"textual":[102],"inputs":[103],"conceptual":[106],"level,":[107],"model":[109,165],"leverages":[110],"descriptions,":[112],"type":[113],"hierarchies,":[114],"relational":[116],"context":[117],"support":[119],"zero-shot":[120],"recognition.":[122],"evaluate":[124],"our":[125],"approach":[126],"on":[127,169],"OVEN":[129],"benchmark,":[130],"large-scale":[132],"open-domain":[133],"dataset":[136],"Wikidata":[138],"IDs":[139],"space.":[143],"Our":[144,163],"experiments":[145],"show":[146],"using":[148],"visual,":[149],"textual,":[150],"knowledge":[153],"greatly":[154],"improves":[155,166],"accuracy,":[156],"especially":[157],"rare":[159],"entities.":[162],"smallest":[164],"accuracy":[168],"10.5%":[173],"compared":[174],"state-of-the-art,":[177],"despite":[178],"being":[179],"35":[180],"times":[181],"smaller.":[182]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}