{"id":"https://openalex.org/W4402352835","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650044","title":"Hierarchical Fusion Framework for Multimodal Dialogue Response Generation","display_name":"Hierarchical Fusion Framework for Multimodal Dialogue Response Generation","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352835","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650044"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5064329321","display_name":"Qi Deng","orcid":"https://orcid.org/0000-0001-5220-5698"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qi Deng","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Computer Science and Engineering,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Computer Science and Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102750692","display_name":"Lijun Wu","orcid":"https://orcid.org/0000-0002-3530-590X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijun Wu","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Computer Science and Engineering,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Computer Science and Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037325282","display_name":"Kaile Su","orcid":"https://orcid.org/0000-0001-6741-9699"},"institutions":[{"id":"https://openalex.org/I11701301","display_name":"Griffith University","ror":"https://ror.org/02sc3r913","country_code":"AU","type":"education","lineage":["https://openalex.org/I11701301"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Kaile Su","raw_affiliation_strings":["Griffith University,School of Information and Communication Technology,Brisbane,Australia"],"affiliations":[{"raw_affiliation_string":"Griffith University,School of Information and Communication Technology,Brisbane,Australia","institution_ids":["https://openalex.org/I11701301"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107837750","display_name":"Wei Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wu","raw_affiliation_strings":["Central South University,School of Computer Science and Engineering,Changsha,China"],"affiliations":[{"raw_affiliation_string":"Central South University,School of Computer Science and Engineering,Changsha,China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100337938","display_name":"Zhiyuan Li","orcid":"https://orcid.org/0000-0002-4616-1841"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Li","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Computer Science and Engineering,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Computer Science and Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061358208","display_name":"Weiwei Duan","orcid":"https://orcid.org/0000-0002-7162-5310"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiwei Duan","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Computer Science and Engineering,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Computer Science and Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5064329321"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.7464,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72040447,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T12031","display_name":"Speech and dialogue systems","score":0.9979000091552734,"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":0.9962000250816345,"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":0.6726700663566589},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5167074203491211},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.493434339761734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42605456709861755},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3052762746810913},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0712757408618927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6726700663566589},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5167074203491211},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.493434339761734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42605456709861755},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3052762746810913},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0712757408618927},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2060727197","https://openalex.org/W2219747066","https://openalex.org/W2560730294","https://openalex.org/W2561715562","https://openalex.org/W2619383789","https://openalex.org/W2896457183","https://openalex.org/W2913668833","https://openalex.org/W2950496566","https://openalex.org/W2950673314","https://openalex.org/W2963498646","https://openalex.org/W3129222583","https://openalex.org/W3159619744","https://openalex.org/W3173018607","https://openalex.org/W3174119180","https://openalex.org/W3184735396","https://openalex.org/W3205638321","https://openalex.org/W4223451840","https://openalex.org/W4229019825","https://openalex.org/W4229042118","https://openalex.org/W4285119160","https://openalex.org/W4312933868","https://openalex.org/W4313131769","https://openalex.org/W4377164418","https://openalex.org/W4385571861","https://openalex.org/W4385572527","https://openalex.org/W4385573236","https://openalex.org/W4386065611","https://openalex.org/W6600043445","https://openalex.org/W6738279954","https://openalex.org/W6748270630","https://openalex.org/W6754005058","https://openalex.org/W6781534913","https://openalex.org/W6784333009","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6811072154","https://openalex.org/W6852934099"],"related_works":["https://openalex.org/W2035104213","https://openalex.org/W2240967841","https://openalex.org/W2791686160","https://openalex.org/W1587348481","https://openalex.org/W1513257435","https://openalex.org/W2289840258","https://openalex.org/W2503352526","https://openalex.org/W2968405290","https://openalex.org/W2960696728","https://openalex.org/W2114040463"],"abstract_inverted_index":{"Two":[0],"analogous":[1],"tasks":[2,18,100],"have":[3],"emerged":[4],"in":[5,65],"multimodal":[6,9,14,30,92,189,214],"dialogue":[7,10,31,93],"research:":[8],"response":[11,23,94],"generation":[12,104],"and":[13,56,75,120,156,165,177,185,216,226],"task-oriented":[15,215],"dialogue.":[16],"Both":[17],"share":[19],"the":[20,29,34,46,196,222],"goal":[21],"of":[22,224],"multi-round,":[24],"interactive":[25],"content":[26],"based":[27,143],"on":[28,37,58,72,144],"history,":[32],"but":[33],"latter":[35],"focuses":[36],"accomplishing":[38],"specific":[39],"objectives":[40,204],"which":[41,158],"can":[42],"be":[43],"viewed":[44],"as":[45,129,202],"former":[47],"fine-tuned.":[48],"The":[49],"fine-tuning":[50],"strategy":[51],"may":[52],"cause":[53],"catastrophic":[54],"forgetting":[55],"overfitting":[57],"few":[59],"well-annotated":[60],"data.":[61],"Despite":[62],"considerable":[63],"progress":[64],"both":[66,213],"areas,":[67],"many":[68],"existing":[69],"works":[70],"rely":[71],"retrieval-based":[73],"approaches":[74],"additional":[76],"auxiliary":[77],"knowledge":[78,167],"bases.":[79],"To":[80],"address":[81],"these":[82,98],"issues,":[83],"we":[84],"propose":[85],"a":[86,103,107,116,130,141],"Hierarchical":[87,149],"Fusion":[88],"Framework":[89],"(HFF)":[90],"for":[91,191],"generation.":[95],"HFF":[96,171,225],"blends":[97],"two":[99],"to":[101,135,205],"learn":[102],"model":[105],"from":[106,168,200],"data-driven":[108],"perspective":[109],"by":[110],"introducing":[111],"multi-dataset":[112,125,201],"learning":[113,126],"scheme,":[114],"achieving":[115],"balance":[117],"between":[118,138,154,198],"generalization":[119],"expertise.":[121],"In":[122],"this":[123],"work,":[124],"is":[127,151],"cast":[128],"multi-objective":[131],"optimization":[132],"problem":[133],"due":[134],"potential":[136],"conflicts":[137],"datasets,":[139,157],"necessitating":[140],"trade-off":[142],"data":[145],"distribution":[146],"during":[147],"training.":[148],"fusion":[150,197],"performed":[152],"sequentially":[153],"modalities":[155],"could":[159],"efficiently":[160],"establish":[161],"clear":[162],"cross-modal":[163,183],"relationships":[164],"integrate":[166],"multi-dataset.":[169],"Specifically,":[170],"aligns":[172],"extracted":[173],"unimodal":[174],"features":[175],"(image":[176],"text)":[178],"before":[179],"fusing":[180],"them":[181,187],"through":[182],"attention":[184],"integrates":[186],"into":[188],"encoder-decoder":[190],"generating":[192],"responses.":[193],"By":[194],"optimizing":[195],"corpora":[199],"conflicting":[203],"satisfy":[206],"Pareto":[207],"optimality,":[208],"our":[209],"approach":[210],"effectively":[211],"facilitates":[212],"task-unoriented":[217],"dialogues.":[218],"Experimental":[219],"results":[220],"demonstrate":[221],"effectiveness":[223],"its":[227],"comparable":[228],"performance":[229],"with":[230],"all":[231],"baselines.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-31T07:56:22.981413","created_date":"2025-10-10T00:00:00"}