{"id":"https://openalex.org/W4308233890","doi":"https://doi.org/10.1109/icip46576.2022.9897623","title":"Relation Enhanced Vision Language Pre-Training","display_name":"Relation Enhanced Vision Language Pre-Training","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4308233890","doi":"https://doi.org/10.1109/icip46576.2022.9897623"},"language":"en","primary_location":{"id":"doi:10.1109/icip46576.2022.9897623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897623","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","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/A5100371930","display_name":"Ju-Hee Lee","orcid":"https://orcid.org/0000-0002-9245-4688"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ju-Hee Lee","raw_affiliation_strings":["Ewha Womans University,Department of Electronic and Electrical Engineering and Graduate Program in Smart Factory,Seoul,Korea","Department of Electronic and Electrical Engineering and Graduate Program in Smart Factory, Ewha Womans University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ewha Womans University,Department of Electronic and Electrical Engineering and Graduate Program in Smart Factory,Seoul,Korea","institution_ids":["https://openalex.org/I138925566"]},{"raw_affiliation_string":"Department of Electronic and Electrical Engineering and Graduate Program in Smart Factory, Ewha Womans University, Seoul, Korea","institution_ids":["https://openalex.org/I138925566"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039192390","display_name":"Je\u2010Won Kang","orcid":"https://orcid.org/0000-0002-1637-9479"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Je-Won Kang","raw_affiliation_strings":["Ewha Womans University,Department of Electronic and Electrical Engineering and Graduate Program in Smart Factory,Seoul,Korea","Department of Electronic and Electrical Engineering and Graduate Program in Smart Factory, Ewha Womans University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ewha Womans University,Department of Electronic and Electrical Engineering and Graduate Program in Smart Factory,Seoul,Korea","institution_ids":["https://openalex.org/I138925566"]},{"raw_affiliation_string":"Department of Electronic and Electrical Engineering and Graduate Program in Smart Factory, Ewha Womans University, Seoul, Korea","institution_ids":["https://openalex.org/I138925566"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.118,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.42116845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2286","last_page":"2290"},"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":0.9987999796867371,"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":0.9916999936103821,"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":0.7073326706886292},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6479596495628357},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.6427476406097412},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6390084028244019},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5904109477996826},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5720087289810181},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5454843044281006},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5292555689811707},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5162632465362549},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4529976546764374},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43664830923080444},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3895655870437622},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3218982517719269},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18517211079597473},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.07672247290611267},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07622140645980835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7073326706886292},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6479596495628357},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.6427476406097412},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6390084028244019},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5904109477996826},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5720087289810181},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5454843044281006},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5292555689811707},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5162632465362549},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4529976546764374},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43664830923080444},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3895655870437622},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3218982517719269},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18517211079597473},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.07672247290611267},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07622140645980835},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip46576.2022.9897623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897623","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2185175083","https://openalex.org/W2277195237","https://openalex.org/W2560730294","https://openalex.org/W2740569051","https://openalex.org/W2745461083","https://openalex.org/W2896457183","https://openalex.org/W2962785943","https://openalex.org/W2963541336","https://openalex.org/W2964187781","https://openalex.org/W2997591391","https://openalex.org/W2998356391","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3094502228","https://openalex.org/W3105232955","https://openalex.org/W3110042533","https://openalex.org/W3173220247","https://openalex.org/W3198196812","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W4388870064","https://openalex.org/W2210139803","https://openalex.org/W4235186151","https://openalex.org/W2054685365","https://openalex.org/W2056057048","https://openalex.org/W2667588871","https://openalex.org/W2272354214","https://openalex.org/W2084768720","https://openalex.org/W2597655663","https://openalex.org/W4281476908"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,67],"propose":[4],"a":[5,13,30,41,48,69,92,100],"relation":[6],"enhanced":[7],"vision-language":[8,21],"pre-training":[9],"(VLP)":[10],"method":[11,113],"for":[12,104,117],"transformer":[14],"model":[15],"(TM)":[16],"to":[17,28,43,77],"improve":[18],"performance":[19,127],"in":[20,47,57],"(V+L)":[22],"tasks.":[23,131],"Current":[24],"VLP":[25,118],"studies":[26],"attempted":[27],"generate":[29,68],"multimodal":[31],"representation":[32,46],"with":[33],"individual":[34],"objects":[35,56,90],"as":[36],"input":[37],"and":[38,91,99,124],"relied":[39],"on":[40,128],"self-attention":[42],"learn":[44],"semantic":[45],"brute":[49],"force":[50],"manner.":[51],"However,":[52],"the":[53,65,79,97,111],"relations":[54,80,121],"among":[55],"an":[58],"image":[59],"are":[60],"largely":[61],"ignored.":[62],"To":[63],"address":[64],"problem,":[66],"paired":[70,89],"visual":[71],"feature":[72],"(PVF)":[73],"that":[74,85,110],"is":[75,102,114],"organized":[76],"express":[78],"between":[81,122],"objects.":[82],"Prior":[83],"knowledge":[84],"reflects":[86],"co-occurrences":[87],"of":[88],"pair-wise":[93],"distance":[94],"matrix":[95],"adjusts":[96],"relations,":[98],"triplet":[101],"used":[103,116],"sentence":[105],"embedding.":[106],"Experimental":[107],"results":[108],"demonstrate":[109],"proposed":[112],"efficiently":[115],"by":[119],"bridging":[120],"objects,":[123],"thus":[125],"improves":[126],"V+L":[129],"downstream":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}