{"id":"https://openalex.org/W4403780545","doi":"https://doi.org/10.1145/3664647.3681219","title":"Caption-Aware Multimodal Relation Extraction with Mutual Information Maximization","display_name":"Caption-Aware Multimodal Relation Extraction with Mutual Information Maximization","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780545","doi":"https://doi.org/10.1145/3664647.3681219"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681219","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5012016681","display_name":"Zefan Zhang","orcid":"https://orcid.org/0000-0001-5627-050X"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zefan Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University & Key Laboratory of Symbolic Computation and Knowledge Engineering, Ministry of Education, Jilin University, Changchun, Jilin, China"],"raw_orcid":"https://orcid.org/0000-0001-5627-050X","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University & Key Laboratory of Symbolic Computation and Knowledge Engineering, Ministry of Education, Jilin University, Changchun, Jilin, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Weiqi Zhang","orcid":"https://orcid.org/0009-0008-0225-1600"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiqi Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University & Key Laboratory of Symbolic Computation and Knowledge Engineering, Ministry of Education, Jilin University, Changchun, Jilin, China"],"raw_orcid":"https://orcid.org/0009-0008-0225-1600","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University & Key Laboratory of Symbolic Computation and Knowledge Engineering, Ministry of Education, Jilin University, Changchun, Jilin, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115601959","display_name":"Yanhui Li","orcid":"https://orcid.org/0009-0006-5270-9814"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanhui Li","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University & Key Laboratory of Symbolic Computation and Knowledge Engineering, Ministry of Education, Jilin University, Changchun, Jilin, China"],"raw_orcid":"https://orcid.org/0009-0006-5270-9814","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University & Key Laboratory of Symbolic Computation and Knowledge Engineering, Ministry of Education, Jilin University, Changchun, Jilin, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088900710","display_name":"Tian Bai","orcid":"https://orcid.org/0000-0001-8060-4725"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian Bai","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University & Key Laboratory of Symbolic Computation and Knowledge Engineering, Ministry of Education, Jilin University, Changchun, Jilin, China"],"raw_orcid":"https://orcid.org/0000-0001-8060-4725","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University & Key Laboratory of Symbolic Computation and Knowledge Engineering, Ministry of Education, Jilin University, Changchun, Jilin, China","institution_ids":["https://openalex.org/I194450716"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I194450716"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1148","last_page":"1157"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9958999752998352,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9937000274658203,"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/mutual-information","display_name":"Mutual information","score":0.8090867400169373},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7420783638954163},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.7138102650642395},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6934175491333008},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.6113395690917969},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5674656629562378},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.471633642911911},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4555160105228424},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3241386413574219},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3147708773612976},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14045274257659912}],"concepts":[{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.8090867400169373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7420783638954163},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.7138102650642395},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6934175491333008},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.6113395690917969},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5674656629562378},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.471633642911911},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4555160105228424},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3241386413574219},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3147708773612976},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14045274257659912},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681219","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2251135946","https://openalex.org/W2788647998","https://openalex.org/W2798298921","https://openalex.org/W2880214242","https://openalex.org/W2987734933","https://openalex.org/W2997045581","https://openalex.org/W3003940182","https://openalex.org/W3035448883","https://openalex.org/W3035524453","https://openalex.org/W3102756401","https://openalex.org/W3127151332","https://openalex.org/W3166051255","https://openalex.org/W3166170409","https://openalex.org/W3176858586","https://openalex.org/W3194836374","https://openalex.org/W3207972321","https://openalex.org/W4285606520","https://openalex.org/W4304080820","https://openalex.org/W4320526408","https://openalex.org/W4379806366","https://openalex.org/W4382317990","https://openalex.org/W4382459184","https://openalex.org/W4384890990","https://openalex.org/W4384891024","https://openalex.org/W4385154451","https://openalex.org/W4385216542","https://openalex.org/W4385570368","https://openalex.org/W4387968001","https://openalex.org/W4387968449","https://openalex.org/W4390872682","https://openalex.org/W4391164085","https://openalex.org/W4392523499","https://openalex.org/W4392904609","https://openalex.org/W4402753759"],"related_works":["https://openalex.org/W2785601041","https://openalex.org/W2241417046","https://openalex.org/W2908598672","https://openalex.org/W2597403208","https://openalex.org/W4307206503","https://openalex.org/W842810586","https://openalex.org/W2393900892","https://openalex.org/W4319940250","https://openalex.org/W2352298027","https://openalex.org/W2092919065"],"abstract_inverted_index":{"Multimodal":[0,66],"Relation":[1,67],"Extraction":[2,68],"(MRE)":[3],"has":[4],"achieved":[5],"great":[6],"improvements.":[7],"However,":[8],"modern":[9],"MRE":[10,134],"models":[11,135],"are":[12,22,34],"easily":[13],"affected":[14],"by":[15],"irrelevant":[16],"objects":[17],"during":[18],"multimodal":[19,123],"alignment":[20],"which":[21],"called":[23],"error":[24],"sensitivity":[25],"issues.":[26],"The":[27],"main":[28],"reason":[29],"is":[30,161],"that":[31,128],"visual":[32,97],"features":[33,40],"not":[35],"fully":[36],"aligned":[37],"with":[38,70],"textual":[39,100],"and":[41,48,99,147,154],"the":[42,52,83,89,95,122,132,137,145],"reasoning":[43,124],"process":[44],"may":[45],"suppress":[46],"redundant":[47],"noisy":[49],"information":[50,109],"at":[51,163],"risk":[53],"of":[54,60,150],"losing":[55],"critical":[56],"information.":[57],"In":[58,104],"light":[59],"this,":[61],"we":[62,76,113],"propose":[63],"a":[64,115],"Caption-Aware":[65,90,152],"Network":[69],"Mutual":[71,116,155],"Information":[72,117,156],"Maximization":[73,118,157],"(CAMIM).":[74],"Specifically,":[75],"first":[77],"generate":[78],"detailed":[79],"image":[80],"captions":[81],"through":[82],"Large":[84],"Language":[85],"Model":[86],"(LLM).":[87],"Then,":[88],"Module":[91,153],"(CAM)":[92],"hierarchically":[93],"aligns":[94],"fine-grained":[96],"entities":[98,101],"for":[102,106],"reasoning.":[103],"addition,":[105],"preserving":[107],"crucial":[108],"within":[110],"different":[111],"modalities,":[112],"leverage":[114],"method":[119],"to":[120],"regulate":[121],"module.":[125],"Experiments":[126],"show":[127],"our":[129,151],"model":[130],"outperforms":[131],"state-of-the-art":[133],"on":[136],"benchmark":[138],"dataset":[139],"MNRE.":[140],"Further":[141],"ablation":[142],"studies":[143],"prove":[144],"pluggable":[146],"effective":[148],"performance":[149],"method.":[158],"Our":[159],"code":[160],"available":[162],"https://github.com/zefanZhang-cn/CAMIM.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}