{"id":"https://openalex.org/W4312975280","doi":"https://doi.org/10.1109/icpr56361.2022.9956261","title":"VReBERT: A Simple and Flexible Transformer for Visual Relationship Detection","display_name":"VReBERT: A Simple and Flexible Transformer for Visual Relationship Detection","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4312975280","doi":"https://doi.org/10.1109/icpr56361.2022.9956261"},"language":"en","primary_location":{"id":"doi:10.1109/icpr56361.2022.9956261","doi":"https://doi.org/10.1109/icpr56361.2022.9956261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956261","pdf_url":null,"source":{"id":"https://openalex.org/S4393916651","display_name":"Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition","issn_l":"1041-3278","issn":["1041-3278","1051-4651"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 26th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2206.09111","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100402010","display_name":"Yu Juan Cui","orcid":"https://orcid.org/0000-0002-1781-4735","observed_orcids":["https://orcid.org/0000-0002-1781-4735"]},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yu Cui","raw_affiliation_strings":["The Australian National University (ANU),Research School of Computer Science","Research School of Computer Science, The Australian National University (ANU)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Australian National University (ANU),Research School of Computer Science","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Research School of Computer Science, The Australian National University (ANU)","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067223903","display_name":"Moshiur R. Farazi","orcid":"https://orcid.org/0000-0003-1494-5921","observed_orcids":["https://orcid.org/0000-0003-1494-5921"]},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Moshiur Farazi","raw_affiliation_strings":["Data61\u2013Commonwealth Scientific and Industrial Research Organisation (CSIRO),Canberra,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data61\u2013Commonwealth Scientific and Industrial Research Organisation (CSIRO),Canberra,Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I42894916"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1615,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.42223581,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":"abs 2001 7966","issue":null,"first_page":"4079","last_page":"4086"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9984999895095825,"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":0.9984999895095825,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0005000000237487257,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.00019999999494757503,"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/visual-relationship-detection","display_name":"visual relationship detection","score":0.9929999709129333},{"id":"https://openalex.org/keywords/multi-stage-training","display_name":"multi-stage training","score":0.7900000214576721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7213091850280762},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.7107710242271423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6203247308731079},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.548650324344635},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.5274006724357605},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4265924096107483},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4259521961212158},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35117024183273315},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3292272388935089},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29478999972343445},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12633880972862244},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icpr56361.2022.9956261","doi":"https://doi.org/10.1109/icpr56361.2022.9956261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956261","pdf_url":null,"source":{"id":"https://openalex.org/S4393916651","display_name":"Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition","issn_l":"1041-3278","issn":["1041-3278","1051-4651"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 26th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2206.09111","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.09111","pdf_url":"https://arxiv.org/pdf/2206.09111","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2206.09111","doi":"https://doi.org/10.48550/arxiv.2206.09111","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2206.09111","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2206.09111","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.09111","pdf_url":"https://arxiv.org/pdf/2206.09111","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4312975280.pdf","grobid_xml":"https://content.openalex.org/works/W4312975280.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1821462560","https://openalex.org/W1933349210","https://openalex.org/W2194775991","https://openalex.org/W2479423890","https://openalex.org/W2505639562","https://openalex.org/W2591644541","https://openalex.org/W2607855566","https://openalex.org/W2626778328","https://openalex.org/W2745461083","https://openalex.org/W2789177853","https://openalex.org/W2789541106","https://openalex.org/W2884822772","https://openalex.org/W2896457183","https://openalex.org/W2950813464","https://openalex.org/W2962737704","https://openalex.org/W2963341956","https://openalex.org/W2963902384","https://openalex.org/W2964072591","https://openalex.org/W2964110616","https://openalex.org/W2968124245","https://openalex.org/W2969047925","https://openalex.org/W2969876226","https://openalex.org/W2970231061","https://openalex.org/W2995273672","https://openalex.org/W3000805499","https://openalex.org/W3001555892","https://openalex.org/W3090449556","https://openalex.org/W3106210592","https://openalex.org/W3138516171"],"related_works":["https://openalex.org/W7066577001","https://openalex.org/W3083917901","https://openalex.org/W2969047925","https://openalex.org/W2982277980","https://openalex.org/W3158495294","https://openalex.org/W3093124244","https://openalex.org/W3119074770","https://openalex.org/W4403888666","https://openalex.org/W3089377493","https://openalex.org/W2998468986"],"abstract_inverted_index":{"Visual":[0,118],"Relationship":[1,119],"Detection":[2,120],"(VRD)":[3],"impels":[4],"a":[5,22,51,77,96,113,122,170],"computer":[6],"vision":[7],"model":[8,98,116,139,162],"to":[9,33,56,80,93,126,142],"see":[10],"beyond":[11],"an":[12,37],"individual":[13],"object":[14,48,66,101],"instance":[15],"and":[16,39,103,130,175],"understand":[17],"how":[18],"different":[19],"objects":[20,35],"in":[21,36,148],"scene":[23],"are":[24,85],"related.":[25],"The":[26],"traditional":[27],"way":[28],"of":[29],"VRD":[30,97,146],"is":[31,54,140],"first":[32],"detect":[34],"image":[38],"then":[40],"separately":[41],"predict":[42,57],"the":[43,46,64,81,144,157,164],"relationship":[44,59,105],"between":[45,63],"detected":[47],"instances.":[49],"Such":[50],"disjoint":[52],"approach":[53],"prone":[55],"redundant":[58],"tags":[60],"(i.e.,":[61],"predicate)":[62],"same":[65],"pair":[67],"with":[68,99,121],"similar":[69,78],"semantic":[70,104,131],"meaning,":[71],"or":[72],"incorrect":[73],"ones":[74],"that":[75,135,154],"have":[76],"meaning":[79],"ground":[82],"truth":[83],"but":[84],"semantically":[86],"incorrect.":[87],"To":[88,107],"remedy":[89],"this,":[90],"we":[91,110,152],"propose":[92,111],"jointly":[94,127],"train":[95],"visual":[100,129],"features":[102],"features.":[106,132],"this":[108],"end,":[109],"VReBERT,":[112],"BERT-like":[114,138],"transformer":[115],"for":[117],"multi-stage":[123],"training":[124],"strategy":[125],"process":[128],"We":[133],"show":[134,153],"our":[136,161],"simple":[137],"able":[141],"outperform":[143],"state-of-the-art":[145,165],"models":[147],"predicate":[149,167],"prediction.":[150],"Furthermore,":[151],"by":[155,169],"using":[156],"pre-trained":[158],"VReBERT":[159],"model,":[160],"pushes":[163],"zero-shot":[166],"prediction":[168],"significant":[171],"margin":[172],"(+8.49":[173],"R@50":[174],"+8.99":[176],"R@100).":[177]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-01-05T00:00:00"}