{"id":"https://openalex.org/W4387968081","doi":"https://doi.org/10.1145/3581783.3612248","title":"Expand BERT Representation with Visual Information via Grounded Language Learning with Multimodal Partial Alignment","display_name":"Expand BERT Representation with Visual Information via Grounded Language Learning with Multimodal Partial Alignment","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968081","doi":"https://doi.org/10.1145/3581783.3612248"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612248","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612248","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612248","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612248","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025645183","display_name":"Cong-Duy Nguyen","orcid":"https://orcid.org/0000-0002-0931-460X"},"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":true,"raw_author_name":"Cong-Duy Nguyen","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-0931-460X","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000620746","display_name":"The-Anh Vu-Le","orcid":"https://orcid.org/0000-0002-4480-5535"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"The-Anh Vu-Le","raw_affiliation_strings":["University of Illinois Urbana-Champaign Illinois, Urbana-Champaign, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-4480-5535","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign Illinois, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103273786","display_name":"Th\u00f4ng Nguyen","orcid":"https://orcid.org/0000-0001-7447-7416"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Thong Nguyen","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7447-7416","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056767671","display_name":"Tho Quan","orcid":"https://orcid.org/0000-0003-0467-6254"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]},{"id":"https://openalex.org/I47265099","display_name":"Ho Chi Minh City University of Technology","ror":"https://ror.org/04qva2324","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I47265099"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Tho Quan","raw_affiliation_strings":["Ho Chi Minh City University of Technology (HCMUT), VNU-HCM, Ho Chi Minh city, Vietnam"],"raw_orcid":"https://orcid.org/0000-0003-0467-6254","affiliations":[{"raw_affiliation_string":"Ho Chi Minh City University of Technology (HCMUT), VNU-HCM, Ho Chi Minh city, Vietnam","institution_ids":["https://openalex.org/I47265099","https://openalex.org/I123565023"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001659855","display_name":"Luu Anh Tuan","orcid":"https://orcid.org/0000-0001-6062-207X"},"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":"Anh-Tuan Luu","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6062-207X","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5025645183"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.3532,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60324711,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5665","last_page":"5673"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9980999827384949,"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/T10028","display_name":"Topic Modeling","score":0.9865999817848206,"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/computer-science","display_name":"Computer science","score":0.8133987188339233},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6280993223190308},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6200906038284302},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5489946603775024},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5461283326148987},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5078292489051819},{"id":"https://openalex.org/keywords/grounded-theory","display_name":"Grounded theory","score":0.46809959411621094},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4666678011417389},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.411683589220047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8133987188339233},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6280993223190308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6200906038284302},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5489946603775024},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5461283326148987},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5078292489051819},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.46809959411621094},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4666678011417389},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.411683589220047},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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/C190248442","wikidata":"https://www.wikidata.org/wiki/Q839486","display_name":"Qualitative research","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581783.3612248","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612248","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612248","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/152626","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/152626","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/152626/1/3581783.3612248.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Association for Computing Machinery","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612248","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612248","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612248","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387968081.pdf","grobid_xml":"https://content.openalex.org/works/W4387968081.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2130643333","https://openalex.org/W2134251538","https://openalex.org/W2250539671","https://openalex.org/W2251939518","https://openalex.org/W2595551253","https://openalex.org/W2962739339","https://openalex.org/W2963264012","https://openalex.org/W2963323070","https://openalex.org/W2963748441","https://openalex.org/W2963804993","https://openalex.org/W2963846996","https://openalex.org/W2963871344","https://openalex.org/W2963918774","https://openalex.org/W2970231061","https://openalex.org/W2970488023","https://openalex.org/W2997591391","https://openalex.org/W3104033643","https://openalex.org/W4210986764","https://openalex.org/W6600411517"],"related_works":["https://openalex.org/W4387929264","https://openalex.org/W3105220303","https://openalex.org/W4287903637","https://openalex.org/W2999168658","https://openalex.org/W69308499","https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W2918609062","https://openalex.org/W2901701848","https://openalex.org/W2310188530"],"abstract_inverted_index":{"Language":[0],"models":[1,162],"have":[2],"been":[3],"supervised":[4],"with":[5,52,96],"both":[6],"language-only":[7],"objective":[8],"and":[9,26,31,71,120,170],"visual":[10,69,123,128],"grounding":[11,124],"in":[12,23,48],"existing":[13],"studies":[14],"of":[15,28,43,75,113,167],"visual-grounded":[16,29,132],"language":[17,32,35,88,118,161,165],"learning.":[18],"However,":[19],"due":[20],"to":[21,38,144],"differences":[22],"the":[24,34,41,44,49,68,72,76,93,105,110,117,146,151,159,168],"distribution":[25],"scale":[27],"datasets":[30],"corpora,":[33,119],"model":[36],"tends":[37],"mix":[39],"up":[40],"context":[42],"tokens":[45],"that":[46,54,91],"occurred":[47],"grounded":[50,87,98],"data":[51],"those":[53],"do":[55],"not.":[56],"As":[57],"a":[58,65,86,122],"result,":[59],"during":[60],"representation":[61,95,112],"learning,":[62],"there":[63],"is":[64],"mismatch":[66],"between":[67,150],"information":[70,129],"contextual":[73,111],"meaning":[74],"sentence.":[77],"To":[78],"overcome":[79],"this":[80],"limitation,":[81],"we":[82,135],"propose":[83],"GroundedBERT":[84,100],"-":[85],"learning":[89],"method":[90,156],"enhances":[92],"BERT":[94,107],"visually":[97],"information.":[99],"comprises":[101],"two":[102,152],"components:":[103],"(i)":[104],"original":[106],"which":[108,126],"captures":[109,127],"words":[114],"learned":[115,130],"from":[116,131],"(ii)":[121],"module":[125],"datasets.":[133,172],"Moreover,":[134],"employ":[136],"Optimal":[137],"Transport":[138],"(OT),":[139],"specifically":[140],"its":[141],"partial":[142],"variant,":[143],"solve":[145],"fractional":[147],"alignment":[148],"problem":[149],"modalities.":[153],"Our":[154],"proposed":[155],"significantly":[157],"outperforms":[158],"baseline":[160],"on":[163],"various":[164],"tasks":[166],"GLUE":[169],"SQuAD":[171]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}