{"id":"https://openalex.org/W4385959364","doi":"https://doi.org/10.1145/3581783.3611810","title":"ZRIGF: An Innovative Multimodal Framework for Zero-Resource Image-Grounded Dialogue Generation","display_name":"ZRIGF: An Innovative Multimodal Framework for Zero-Resource Image-Grounded Dialogue Generation","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4385959364","doi":"https://doi.org/10.1145/3581783.3611810"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611810","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611810","pdf_url":null,"source":null,"license":null,"license_id":null,"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":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.00400","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077216037","display_name":"Bo Zhang","orcid":"https://orcid.org/0000-0001-6933-922X"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zhang","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-6933-922X","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100370452","display_name":"Jian Wang","orcid":"https://orcid.org/0000-0002-4656-7446"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Wang","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-4656-7446","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452344","display_name":"Hui Ma","orcid":"https://orcid.org/0000-0002-7146-8036"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Ma","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-7146-8036","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062895972","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0001-5453-978X"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-5453-978X","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023931221","display_name":"Hongfei Lin","orcid":"https://orcid.org/0000-0003-0872-7688"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongfei Lin","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-0872-7688","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5464","last_page":"5473"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9873999953269958,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9854000210762024,"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":0.771493673324585},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5736826062202454},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5571460723876953},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5454108119010925},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5357949137687683},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5138338208198547},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4920904040336609},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4436303377151489},{"id":"https://openalex.org/keywords/grounded-theory","display_name":"Grounded theory","score":0.43958476185798645},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4154210090637207},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38293683528900146},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11888298392295837},{"id":"https://openalex.org/keywords/qualitative-research","display_name":"Qualitative research","score":0.08738470077514648},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07585486769676208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.771493673324585},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5736826062202454},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5571460723876953},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5454108119010925},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5357949137687683},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5138338208198547},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4920904040336609},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4436303377151489},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.43958476185798645},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4154210090637207},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38293683528900146},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11888298392295837},{"id":"https://openalex.org/C190248442","wikidata":"https://www.wikidata.org/wiki/Q839486","display_name":"Qualitative research","level":2,"score":0.08738470077514648},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07585486769676208},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581783.3611810","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611810","pdf_url":null,"source":null,"license":null,"license_id":null,"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:arXiv.org:2308.00400","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.00400","pdf_url":"https://arxiv.org/pdf/2308.00400","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.00400","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.00400","pdf_url":"https://arxiv.org/pdf/2308.00400","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6126655695","display_name":null,"funder_award_id":"No. 62006034","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7575631531","display_name":null,"funder_award_id":"62006034","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385959364.pdf","grobid_xml":"https://content.openalex.org/works/W4385959364.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1593271688","https://openalex.org/W1861492603","https://openalex.org/W2130942839","https://openalex.org/W2133012565","https://openalex.org/W2154652894","https://openalex.org/W2476548250","https://openalex.org/W2583186419","https://openalex.org/W2612690371","https://openalex.org/W2775774141","https://openalex.org/W2783549597","https://openalex.org/W2795571593","https://openalex.org/W2908510526","https://openalex.org/W2945260553","https://openalex.org/W2963206148","https://openalex.org/W2963331137","https://openalex.org/W2963903950","https://openalex.org/W2964007535","https://openalex.org/W2972916088","https://openalex.org/W2979826702","https://openalex.org/W2988937804","https://openalex.org/W2998563994","https://openalex.org/W2999905431","https://openalex.org/W3007008027","https://openalex.org/W3015063797","https://openalex.org/W3034999214","https://openalex.org/W3035448310","https://openalex.org/W3093096176","https://openalex.org/W3093427098","https://openalex.org/W3094502228","https://openalex.org/W3121480429","https://openalex.org/W3152929911","https://openalex.org/W3152943448","https://openalex.org/W3166396011","https://openalex.org/W3173864402","https://openalex.org/W3197259906","https://openalex.org/W3199193983","https://openalex.org/W3206527789","https://openalex.org/W4214540501","https://openalex.org/W4220775189","https://openalex.org/W4223938549","https://openalex.org/W4250928698","https://openalex.org/W4288083516","https://openalex.org/W4303492595","https://openalex.org/W4304080179","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W1546533203","https://openalex.org/W2054080977","https://openalex.org/W1511554945","https://openalex.org/W2015439768","https://openalex.org/W4361008414","https://openalex.org/W3040823075","https://openalex.org/W2092147963","https://openalex.org/W2620765995","https://openalex.org/W1535784397","https://openalex.org/W3140115162"],"abstract_inverted_index":{"Image-grounded":[0],"dialogue":[1,53,136,158],"systems":[2],"benefit":[3],"greatly":[4],"from":[5],"integrating":[6],"visual":[7,99],"information,":[8],"resulting":[9],"in":[10,23,55,141,155,167],"high-quality":[11],"response":[12],"generation.":[13],"However,":[14],"current":[15],"models":[16],"struggle":[17],"to":[18,28,119,160],"effectively":[19],"utilize":[20],"such":[21],"information":[22,51,116],"zero-resource":[24,56,153],"scenarios,":[25],"mainly":[26],"due":[27],"the":[29,156],"disparity":[30],"between":[31],"image":[32,93],"and":[33,67,80,101,114,134,145],"text":[34],"modalities.":[35],"To":[36],"overcome":[37],"this":[38],"challenge,":[39],"we":[40,149],"propose":[41],"an":[42,115],"innovative":[43],"multimodal":[44,104,111,126],"framework,":[45],"called":[46],"ZRIGF,":[47],"which":[48],"assimilates":[49],"image-grounded":[50,135,157],"for":[52],"generation":[54],"situations.":[57],"ZRIGF":[58],"implements":[59],"a":[60,73,83,90,110,151],"two-stage":[61],"learning":[62],"strategy,":[63],"comprising":[64],"contrastive":[65],"pre-training":[66,71,98,108],"generative":[68],"pre-training.":[69],"Contrastive":[70],"includes":[72],"text-image":[74],"matching":[75],"module":[76,95,113,118],"that":[77,96],"maps":[78],"images":[79],"texts":[81],"into":[82],"unified":[84],"encoded":[85],"vector":[86],"space,":[87],"along":[88],"with":[89],"text-assisted":[91],"masked":[92],"modeling":[94],"preserves":[97],"features":[100],"fosters":[102],"further":[103],"feature":[105],"alignment.":[106],"Generative":[107],"employs":[109],"fusion":[112],"transfer":[117],"produce":[120],"insightful":[121],"responses":[122],"based":[123],"on":[124,131],"harmonized":[125],"representations.":[127],"Comprehensive":[128],"experiments":[129],"conducted":[130],"both":[132],"text-based":[133],"datasets":[137],"demonstrate":[138,161],"ZRIGF's":[139],"efficacy":[140],"generating":[142],"contextually":[143],"pertinent":[144],"informative":[146],"responses.":[147],"Furthermore,":[148],"adopt":[150],"fully":[152],"scenario":[154],"dataset":[159],"our":[162],"framework's":[163],"robust":[164],"generalization":[165],"capabilities":[166],"novel":[168],"domains.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
