{"id":"https://openalex.org/W4312493728","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892884","title":"ICAF: Iterative Contrastive Alignment Framework for Multimodal Abstractive Summarization","display_name":"ICAF: Iterative Contrastive Alignment Framework for Multimodal Abstractive Summarization","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312493728","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892884"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892884","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892884","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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/A5101964976","display_name":"Zijian Zhang","orcid":"https://orcid.org/0000-0001-8308-768X"},"institutions":[{"id":"https://openalex.org/I4210156189","display_name":"Shanghai Dianji University","ror":"https://ror.org/055fene14","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210156189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijian Zhang","raw_affiliation_strings":["Meituan-Dianping Group,Shanghai,China","Meituan-Dianping Group, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan-Dianping Group,Shanghai,China","institution_ids":["https://openalex.org/I4210156189"]},{"raw_affiliation_string":"Meituan-Dianping Group, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101809228","display_name":"Chang Shu","orcid":"https://orcid.org/0000-0001-8719-3690"},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]},{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Shu","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd,Shenzhen,China","University of Nottingham Ningbo China, Ningbo, China","Ping An Technology (Shenzhen) Co., Ltd, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd,Shenzhen,China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]},{"raw_affiliation_string":"University of Nottingham Ningbo China, Ningbo, China","institution_ids":["https://openalex.org/I13591777"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000122982","display_name":"Youxin Chen","orcid":"https://orcid.org/0000-0002-7231-5058"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youxin Chen","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd,Shenzhen,China","Ping An Technology (Shenzhen) Co., Ltd, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd,Shenzhen,China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070173803","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0002-5242-7909"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd,Shenzhen,China","Ping An Technology (Shenzhen) Co., Ltd, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd,Shenzhen,China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401561","display_name":"Qian Zhang","orcid":"https://orcid.org/0000-0001-5562-4759"},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Zhang","raw_affiliation_strings":["University of Nottingham Ningbo China,Ningbo,China","University of Nottingham Ningbo China, Ningbo, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Nottingham Ningbo China,Ningbo,China","institution_ids":["https://openalex.org/I13591777"]},{"raw_affiliation_string":"University of Nottingham Ningbo China, Ningbo, China","institution_ids":["https://openalex.org/I13591777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100414937","display_name":"Lu Zheng","orcid":"https://orcid.org/0000-0001-5079-4169"},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Zheng","raw_affiliation_strings":["University of Nottingham Ningbo China,Ningbo,China","University of Nottingham Ningbo China, Ningbo, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Nottingham Ningbo China,Ningbo,China","institution_ids":["https://openalex.org/I13591777"]},{"raw_affiliation_string":"University of Nottingham Ningbo China, Ningbo, China","institution_ids":["https://openalex.org/I13591777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6229,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.68396501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/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/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.855272650718689},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.5978204607963562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5756551027297974},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5530270338058472},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46457892656326294},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.428928017616272}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.855272650718689},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.5978204607963562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5756551027297974},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5530270338058472},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46457892656326294},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.428928017616272},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892884","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892884","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6700000166893005,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W2133564696","https://openalex.org/W2154652894","https://openalex.org/W2510403706","https://openalex.org/W2593341061","https://openalex.org/W2606974598","https://openalex.org/W2774267535","https://openalex.org/W2809191921","https://openalex.org/W2842511635","https://openalex.org/W2890721473","https://openalex.org/W2891533927","https://openalex.org/W2899274165","https://openalex.org/W2945260553","https://openalex.org/W2962964995","https://openalex.org/W2963407669","https://openalex.org/W2970231061","https://openalex.org/W2970419734","https://openalex.org/W2970641574","https://openalex.org/W2980884691","https://openalex.org/W2986670728","https://openalex.org/W2997326549","https://openalex.org/W2998733554","https://openalex.org/W3034999214","https://openalex.org/W3091588028","https://openalex.org/W3094502228","https://openalex.org/W3100439847","https://openalex.org/W3104210310","https://openalex.org/W3115803208","https://openalex.org/W3137278571","https://openalex.org/W3156636935","https://openalex.org/W3165529210","https://openalex.org/W3174700550","https://openalex.org/W3176675602","https://openalex.org/W3199294715","https://openalex.org/W4214493665","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6679434410","https://openalex.org/W6682631176","https://openalex.org/W6739901393","https://openalex.org/W6755559483","https://openalex.org/W6784333009","https://openalex.org/W6787997112","https://openalex.org/W6791943378"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4306886878","https://openalex.org/W2740913191","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Integrating":[0],"multimodal":[1],"knowledge":[2],"for":[3,46],"abstractive":[4],"summarization":[5],"task":[6],"is":[7],"a":[8,97],"work-in-progress":[9],"research":[10],"area,":[11],"with":[12],"present":[13],"techniques":[14],"inheriting":[15],"fusion-then-generation":[16],"paradigm.":[17],"Due":[18],"to":[19,44,50,64,86,102,126,133],"semantic":[20],"gaps":[21],"between":[22,90,108],"computer":[23],"vision":[24],"and":[25,39,84,92,111,137,157],"natural":[26],"language":[27],"processing,":[28],"current":[29],"methods":[30],"often":[31],"treat":[32],"multiple":[33],"data":[34],"points":[35],"as":[36],"separate":[37],"objects":[38],"rely":[40],"on":[41,146,150],"attention":[42],"mechanisms":[43],"search":[45],"connection":[47],"in":[48],"order":[49],"fuse":[51],"together.":[52],"In":[53],"addition,":[54],"missing":[55],"awareness":[56],"of":[57,153],"cross-modal":[58],"matching":[59],"from":[60],"many":[61],"frameworks":[62],"leads":[63],"performance":[65],"reduction.":[66],"To":[67],"solve":[68],"these":[69],"two":[70],"drawbacks,":[71],"we":[72,95],"propose":[73],"an":[74],"Iterative":[75],"Contrastive":[76],"Alignment":[77],"Framework":[78],"(ICAF)":[79],"that":[80],"uses":[81],"recurrent":[82,98],"alignment":[83,99],"contrast":[85],"capture":[87],"the":[88,118,129,143,151],"coherences":[89],"images":[91],"texts.":[93],"Specifically,":[94],"design":[96],"(RA)":[100],"layer":[101],"gradually":[103],"investigate":[104],"fine-grained":[105],"semantical":[106],"relationships":[107],"image":[109],"patches":[110],"text":[112],"tokens.":[113],"At":[114],"each":[115],"step":[116],"during":[117],"encoding":[119],"process,":[120],"crossmodal":[121],"contrastive":[122],"losses":[123],"are":[124],"applied":[125],"directly":[127],"optimize":[128],"embedding":[130],"space.":[131],"According":[132],"ROUGE,":[134],"relevance":[135],"scores,":[136],"human":[138],"evaluation,":[139],"our":[140,154],"model":[141],"outperforms":[142],"state-of-the-art":[144],"baselines":[145],"MSMO":[147],"dataset.":[148],"Experiments":[149],"applicability":[152],"proposed":[155],"framework":[156],"hyperparameters":[158],"settings":[159],"have":[160],"been":[161],"also":[162],"conducted.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}