{"id":"https://openalex.org/W4415068847","doi":"https://doi.org/10.1145/3805622.3810805","title":"On the Effectiveness of Integration Methods for Multimodal Dialogue Response Retrieval","display_name":"On the Effectiveness of Integration Methods for Multimodal Dialogue Response Retrieval","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W4415068847","doi":"https://doi.org/10.1145/3805622.3810805"},"language":"en","primary_location":{"id":"doi:10.1145/3805622.3810805","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810805","pdf_url":null,"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 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810805","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Seongbo Jang","orcid":"https://orcid.org/0009-0008-3398-0144"},"institutions":[{"id":"https://openalex.org/I89440247","display_name":"Myongji University","ror":"https://ror.org/00s9dpb54","country_code":"KR","type":"education","lineage":["https://openalex.org/I89440247"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seongbo Jang","raw_affiliation_strings":["Myongji University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0008-3398-0144","affiliations":[{"raw_affiliation_string":"Myongji University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I89440247"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069648320","display_name":"Seonghyeon Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seonghyeon Lee","raw_affiliation_strings":["Kyungpook National University, Daegu, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0002-0039-8920","affiliations":[{"raw_affiliation_string":"Kyungpook National University, Daegu, Republic of Korea","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071595184","display_name":"Dongha Lee","orcid":"https://orcid.org/0000-0003-2173-3476"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongha Lee","raw_affiliation_strings":["Yonsei University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-2173-3476","affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045521125","display_name":"Hwanjo Yu","orcid":"https://orcid.org/0000-0002-7510-0255"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hwanjo Yu","raw_affiliation_strings":["Pohang University of Science and Technology, Pohang, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-7510-0255","affiliations":[{"raw_affiliation_string":"Pohang University of Science and Technology, Pohang, Republic of Korea","institution_ids":["https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00717489,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1787","last_page":"1792"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9975000023841858,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9975000023841858,"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":0.9800000190734863,"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":0.9333000183105469,"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/multimodality","display_name":"Multimodality","score":0.7720000147819519},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7006999850273132},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6438000202178955},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.3944000005722046},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.32199999690055847},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.31859999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7943000197410583},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.7720000147819519},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7006999850273132},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6438000202178955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5443000197410583},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.3944000005722046},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3666999936103821},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33169999718666077},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32350000739097595},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32199999690055847},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.25949999690055847}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3805622.3810805","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810805","pdf_url":null,"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 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.11499","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2506.11499","pdf_url":"https://arxiv.org/pdf/2506.11499","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.11499","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.11499","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810805","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810805","pdf_url":null,"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 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"chatbots":[1],"have":[2,20],"become":[3],"one":[4],"of":[5,26,69,93,128],"the":[6,24,67,89,103,114,126,138,141],"major":[7],"topics":[8],"for":[9,63],"dialogue":[10,31,38,59],"systems":[11,65],"in":[12,43,113],"both":[13],"research":[14],"community":[15],"and":[16,49,83,87,91,140],"industry.":[17],"Recently,":[18],"researchers":[19],"shed":[21],"light":[22],"on":[23,79,98],"multimodality":[25],"responses":[27,42],"as":[28,30,47,66],"well":[29],"contexts.":[32],"This":[33],"work":[34],"explores":[35],"how":[36],"a":[37,57,80,119],"system":[39],"can":[40],"output":[41],"various":[44],"modalities":[45],"such":[46],"text":[48],"image.":[50],"To":[51],"this":[52],"end,":[53],"we":[54],"first":[55],"formulate":[56],"multimodal":[58],"response":[60],"retrieval":[61],"task":[62],"retrieval-based":[64],"combination":[68],"three":[70,75],"subtasks.":[71],"We":[72],"then":[73],"propose":[74],"integration":[76],"methods":[77],"based":[78],"two-step":[81,115],"approach":[82,105],"an":[84,110],"end-to-end":[85,104],"approach,":[86],"compare":[88],"merits":[90],"demerits":[92],"each":[94],"method.":[95],"Experimental":[96],"results":[97],"two":[99],"datasets":[100],"demonstrate":[101],"that":[102],"achieves":[106],"comparable":[107],"performance":[108,133],"without":[109],"intermediate":[111],"step":[112],"approach.":[116],"In":[117],"addition,":[118],"parameter":[120],"sharing":[121],"strategy":[122],"not":[123],"only":[124],"reduces":[125],"number":[127],"parameters":[129],"but":[130],"also":[131],"boosts":[132],"by":[134],"transferring":[135],"knowledge":[136],"across":[137],"subtasks":[139],"modalities.":[142]},"counts_by_year":[],"updated_date":"2026-06-17T06:14:20.161405","created_date":"2025-10-11T00:00:00"}