{"id":"https://openalex.org/W4399418732","doi":"https://doi.org/10.1145/3652583.3658016","title":"ML <sup>2</sup> MG-VLCR: A Multimodal LLM Guided Zero-shot Method for Visio-linguistic Compositional Reasoning with Autoregressive Generative Language Model","display_name":"ML <sup>2</sup> MG-VLCR: A Multimodal LLM Guided Zero-shot Method for Visio-linguistic Compositional Reasoning with Autoregressive Generative Language Model","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399418732","doi":"https://doi.org/10.1145/3652583.3658016"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3658016","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658016","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658016","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","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/10.1145/3652583.3658016","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045374497","display_name":"Ziyu Gong","orcid":"https://orcid.org/0009-0008-0525-3089"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ziyu Gong","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0008-0525-3089","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074496629","display_name":"Chengcheng Mai","orcid":"https://orcid.org/0000-0002-6185-8858"},"institutions":[{"id":"https://openalex.org/I152031979","display_name":"Nanjing Normal University","ror":"https://ror.org/036trcv74","country_code":"CN","type":"education","lineage":["https://openalex.org/I152031979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengcheng Mai","raw_affiliation_strings":["School of Computer Science and Electronic Information/School of Artifical Intelligence, Nanjing Normal University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-6185-8858","affiliations":[{"raw_affiliation_string":"School of Computer Science and Electronic Information/School of Artifical Intelligence, Nanjing Normal University, Nanjing, China","institution_ids":["https://openalex.org/I152031979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007538828","display_name":"Yihua Huang","orcid":"https://orcid.org/0000-0003-1806-0936"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihua Huang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-1806-0936","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045374497"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06971436,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"842","last_page":"850"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9915000200271606,"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":0.7075327634811401},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6397224068641663},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6372753381729126},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6333750486373901},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6310244798660278},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6169797778129578},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5667724609375},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.539110004901886},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4230560064315796},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4229254126548767},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3254443407058716},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.28043854236602783},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19150316715240479},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08732485771179199}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7075327634811401},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6397224068641663},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6372753381729126},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6333750486373901},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6310244798660278},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6169797778129578},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5667724609375},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.539110004901886},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4230560064315796},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4229254126548767},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3254443407058716},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.28043854236602783},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19150316715240479},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08732485771179199},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652583.3658016","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658016","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658016","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3652583.3658016","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658016","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658016","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.46000000834465027,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5372072380","display_name":null,"funder_award_id":"U1811461","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5922060040","display_name":null,"funder_award_id":"U1811461","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G6481624893","display_name":null,"funder_award_id":"61572250","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399418732.pdf","grobid_xml":"https://content.openalex.org/works/W4399418732.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2962739339","https://openalex.org/W2970785793","https://openalex.org/W3126337491","https://openalex.org/W3126464137","https://openalex.org/W3126792443","https://openalex.org/W3135367836","https://openalex.org/W3166396011","https://openalex.org/W3167118264","https://openalex.org/W3214685499","https://openalex.org/W4226182655","https://openalex.org/W4312933868","https://openalex.org/W4313178921","https://openalex.org/W4366330503","https://openalex.org/W4366850747","https://openalex.org/W4367367040","https://openalex.org/W4375869762","https://openalex.org/W4376312115","https://openalex.org/W4380558379","https://openalex.org/W4382490555","https://openalex.org/W4382491206","https://openalex.org/W4386185600","https://openalex.org/W4388482029","https://openalex.org/W4389665280","https://openalex.org/W6600339457"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559","https://openalex.org/W4299831724","https://openalex.org/W4283803360"],"abstract_inverted_index":{"The":[0],"visio-linguistic":[1,95],"compositional":[2,68,96,137,201],"reasoning":[3,69,97],"is":[4],"an":[5,113,145,177],"interesting":[6],"but":[7,24,35],"challenging":[8],"task":[9],"aimed":[10],"at":[11],"matching":[12,42,148],"two":[13,16,20,26],"images":[14,21,206],"and":[15,57,81,107,115,183,190,203,207],"captions,":[17],"where":[18,170],"the":[19,25,32,41,46,51,55,58,61,78,102,132,136,154,158,163,193,200],"are":[22,29,74],"different":[23,37,119],"corresponding":[27],"captions":[28],"composed":[30],"of":[31,54,60,104,139,157,195,205],"same":[33],"words":[34],"in":[36,180,198],"order.":[38,143],"This":[39],"requires":[40],"model":[43,174],"to":[44,48,77,126,131],"have":[45],"ability":[47],"understand":[49],"both":[50],"composition":[52],"structure":[53,80,138,202],"image":[56,79,114,140,165],"order":[59,120,181,204],"description":[62],"text.":[63],"However,":[64],"when":[65],"faced":[66],"with":[67,101,118],"tasks,":[70],"existing":[71],"vision-language":[72],"models":[73],"not":[75],"sensitive":[76],"text":[82,129,142,160],"order,":[83],"acting":[84],"more":[85],"like":[86],"bag-of-words":[87],"models.":[88],"To":[89],"address":[90],"this":[91],"challenge,":[92],"a":[93],"zero-shot":[94],"method":[98,149,197],"was":[99,150],"proposed":[100,151],"assistance":[103],"multimodal":[105],"LLM":[106],"autoregressive":[108,171],"generative":[109,172],"language":[110,173],"model.":[111],"Given":[112],"candidate":[116,159],"texts":[117],"compositions,":[121],"we":[122],"first":[123],"leveraged":[124],"LLaVA":[125],"generate":[127],"descriptive":[128],"according":[130],"image,":[133],"for":[134],"reflecting":[135],"into":[141],"Then,":[144],"order-sensitive":[146],"image-text":[147],"by":[152,168],"calculating":[153],"generation":[155],"probability":[156],"conditioned":[161],"on":[162,187],"textualized":[164],"information":[166],"obtained":[167],"LLaVA,":[169],"explicitly":[175],"plays":[176],"important":[178],"role":[179],"modeling":[182],"evaluating.":[184],"Experimental":[185],"results":[186],"VG-Relation,":[188],"VG-Attribution":[189],"Flickr30K-Order,":[191],"demonstrated":[192],"superiority":[194],"our":[196],"understanding":[199],"texts.":[208]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}