{"id":"https://openalex.org/W4415708121","doi":"https://doi.org/10.1109/icme59968.2025.11208999","title":"An End-to-End Model for Photo-Sharing Multi-Modal Dialogue Generation","display_name":"An End-to-End Model for Photo-Sharing Multi-Modal Dialogue Generation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708121","doi":"https://doi.org/10.1109/icme59968.2025.11208999"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11208999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5060506052","display_name":"Peiming Guo","orcid":"https://orcid.org/0000-0002-0890-2290"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiming Guo","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055794780","display_name":"Sinuo Liu","orcid":"https://orcid.org/0000-0003-2232-6469"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sinuo Liu","raw_affiliation_strings":["The University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103114439","display_name":"Yanzhao Zhang","orcid":"https://orcid.org/0000-0003-2894-4727"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanzhao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049484480","display_name":"Dingkun Long","orcid":"https://orcid.org/0000-0001-6570-9406"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dingkun Long","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101159930","display_name":"Pengju Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengju Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004953265","display_name":"Meishan Zhang","orcid":"https://orcid.org/0000-0001-6335-1340"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meishan Zhang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052195927","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0001-5812-9518"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9879999756813049,"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":0.9879999756813049,"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":0.0024999999441206455,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0024999999441206455,"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/pipeline","display_name":"Pipeline (software)","score":0.765500009059906},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6385999917984009},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6158000230789185},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6141999959945679},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.515500009059906},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5060999989509583},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.45179998874664307},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.44029998779296875},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.4108000099658966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922999858856201},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.765500009059906},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6385999917984009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6312999725341797},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6158000230789185},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6141999959945679},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.515500009059906},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5060999989509583},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4560999870300293},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.44029998779296875},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43479999899864197},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.4108000099658966},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3822999894618988},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3222000002861023},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.30559998750686646},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.2687000036239624},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11208999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W3035448310","https://openalex.org/W3174119180","https://openalex.org/W3176450677","https://openalex.org/W3180355996","https://openalex.org/W3205638321","https://openalex.org/W4249013746","https://openalex.org/W4385571466","https://openalex.org/W4401042377","https://openalex.org/W4401043376","https://openalex.org/W4402670339","https://openalex.org/W4402754134"],"related_works":[],"abstract_inverted_index":{"Photo-Sharing":[0],"Multi-modal":[1],"dialogue":[2,6,74,103],"generation":[3,40,45,137],"requires":[4],"a":[5,30,38,115,144],"agent":[7],"not":[8],"only":[9],"to":[10,16,47,127,155,178],"generate":[11],"text":[12,25,39,58,88,197],"responses":[13],"but":[14],"also":[15],"share":[17],"photos":[18],"at":[19],"the":[20,28,55,72,77,81,96,124,132,139,157,187],"proper":[21],"moment.":[22],"Using":[23],"image":[24,35,44,87,108,112,136,199],"caption":[26,36],"as":[27],"bridge,":[29],"pipeline":[31,78,185],"model":[32,46,79,99,122,160,164,189],"integrates":[33,106],"an":[34,43,107,111],"model,":[37,41],"and":[42,65,67,110,149,152,161,165,175,198],"handle":[48],"this":[49],"complex":[50,73],"multi-modal":[51,102],"task.":[52],"However,":[53],"representing":[54],"images":[56,130],"with":[57,114,184],"captions":[59,89],"may":[60],"lose":[61],"important":[62],"visual":[63,129],"details":[64],"information":[66],"cause":[68],"error":[69],"propagation":[70],"in":[71,131,138],"system.":[75],"Besides,":[76],"isolates":[80],"three":[82],"models":[83],"separately":[84],"because":[85],"discrete":[86],"hinder":[90],"end-to-end":[91,98,167,181,188],"gradient":[92,168],"propagation.":[93,169],"We":[94,170],"propose":[95,143],"first":[97],"for":[100],"photo-sharing":[101],"generation,":[104],"which":[105],"perceptron":[109],"generator":[113],"large":[116,120,158],"language":[117,121,159],"model.":[118,182],"The":[119],"employs":[123],"vision":[125],"encoder":[126],"perceive":[128],"input":[133],"end.":[134],"For":[135],"output":[140],"end,":[141],"we":[142],"dynamic":[145],"vocabulary":[146],"transformation":[147],"matrix":[148],"use":[150],"straight-through":[151],"gumbel-softmax":[153],"techniques":[154],"align":[156],"stable":[162],"diffusion":[163],"achieve":[166],"perform":[171],"experiments":[172],"on":[173,193],"PhotoChat":[174],"DialogCC":[176],"datasets":[177],"evaluate":[179],"our":[180],"Compared":[183],"models,":[186],"gains":[190],"state-of-the-art":[191],"performances":[192],"various":[194],"metrics":[195],"of":[196],"generation.":[200]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}