{"id":"https://openalex.org/W4403780666","doi":"https://doi.org/10.1145/3664647.3681367","title":"Shapley Value-based Contrastive Alignment for Multimodal Information Extraction","display_name":"Shapley Value-based Contrastive Alignment for Multimodal Information Extraction","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780666","doi":"https://doi.org/10.1145/3664647.3681367"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681367","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681367","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":"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":null,"display_name":"Wen Luo","orcid":"https://orcid.org/0009-0004-8766-3073"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wen Luo","raw_affiliation_strings":["State Key Laboratory of Multimedia Information Processing, Peking University & School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-8766-3073","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing, Peking University & School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100694663","display_name":"Yu Xia","orcid":"https://orcid.org/0000-0002-8760-4397"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Xia","raw_affiliation_strings":["State Key Laboratory of Multimedia Information Processing, Peking University & School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8760-4397","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing, Peking University & School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030280741","display_name":"Tianshu Shen","orcid":"https://orcid.org/0000-0003-2693-8374"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shen Tianshu","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-0333-6588","affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058353424","display_name":"Sujian Li","orcid":"https://orcid.org/0000-0001-7493-0786"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sujian Li","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7493-0786","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":1.8608,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.87209699,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5270","last_page":"5279"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9994999766349792,"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":0.9973000288009644,"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":0.6381368041038513},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4952932894229889},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4821150302886963},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4697102904319763},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4513779878616333},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3642292618751526},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35172826051712036},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14736291766166687}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6381368041038513},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4952932894229889},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4821150302886963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4697102904319763},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4513779878616333},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3642292618751526},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35172826051712036},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14736291766166687},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681367","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681367","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1528012351","https://openalex.org/W1968958679","https://openalex.org/W2073231946","https://openalex.org/W2745461083","https://openalex.org/W2788647998","https://openalex.org/W2798298921","https://openalex.org/W2964022985","https://openalex.org/W2970773487","https://openalex.org/W3003940182","https://openalex.org/W3035448883","https://openalex.org/W3047144459","https://openalex.org/W3092692431","https://openalex.org/W3127151332","https://openalex.org/W3166170409","https://openalex.org/W3173220247","https://openalex.org/W3175300676","https://openalex.org/W3176858586","https://openalex.org/W3207972321","https://openalex.org/W4212998232","https://openalex.org/W4225323055","https://openalex.org/W4225757376","https://openalex.org/W4229024390","https://openalex.org/W4293518017","https://openalex.org/W4304015092","https://openalex.org/W4382317693","https://openalex.org/W4382466550","https://openalex.org/W4385574193"],"related_works":["https://openalex.org/W2377297411","https://openalex.org/W3148217948","https://openalex.org/W2375788636","https://openalex.org/W2358561207","https://openalex.org/W2388704129","https://openalex.org/W2392827053","https://openalex.org/W2975617233","https://openalex.org/W2377877252","https://openalex.org/W2362914816","https://openalex.org/W2368651715"],"abstract_inverted_index":{"The":[0],"rise":[1],"of":[2,9,54,111,117],"social":[3],"media":[4],"and":[5,39,44,92,120,125],"the":[6,98,108,115,140,148],"exponential":[7],"growth":[8],"multimodal":[10,59],"communication":[11],"necessitates":[12],"advanced":[13],"techniques":[14],"for":[15,160],"Multimodal":[16],"Information":[17],"Extraction":[18],"(MIE).":[19],"However,":[20],"existing":[21,176],"methodologies":[22],"primarily":[23],"rely":[24],"on":[25],"direct":[26],"Image-Text":[27],"interactions,":[28],"a":[29,51,80,132],"paradigm":[30,53],"that":[31,171],"often":[32],"faces":[33],"significant":[34],"challenges":[35],"due":[36],"to":[37,64,69,106,138],"semantic":[38,124],"modality":[40,126],"gaps":[41],"between":[42],"images":[43,121],"text.":[45],"In":[46,73],"this":[47,76,129],"paper,":[48],"we":[49,78,154],"introduce":[50],"new":[52],"Image-Context-Text":[55],"interaction,":[56],"where":[57],"large":[58],"models":[60],"(LMMs)":[61],"are":[62],"utilized":[63],"generate":[65],"descriptive":[66],"textual":[67],"context":[68],"bridge":[70],"these":[71,151],"gaps.":[72],"line":[74],"with":[75],"paradigm,":[77],"propose":[79],"novel":[81],"Shapley":[82,99],"Value-based":[83],"Contrastive":[84],"Alignment":[85],"(Shap-CA)":[86],"method,":[87],"which":[88],"aligns":[89],"both":[90],"context-text":[91],"context-image":[93],"pairs.":[94,152],"Shap-CA":[95],"initially":[96],"applies":[97],"value":[100],"concept":[101],"from":[102],"cooperative":[103],"game":[104],"theory":[105],"assess":[107],"individual":[109],"contribution":[110,142],"each":[112],"element":[113],"in":[114],"set":[116],"contexts,":[118],"texts":[119],"towards":[122],"total":[123],"overlaps.":[127],"Following":[128],"quantitative":[130],"evaluation,":[131],"contrastive":[133],"learning":[134],"strategy":[135],"is":[136],"employed":[137],"enhance":[139],"interactive":[141],"within":[143],"context-text/image":[144],"pairs,":[145],"while":[146],"minimizing":[147],"influence":[149],"across":[150,166],"Furthermore,":[153],"design":[155],"an":[156],"adaptive":[157],"fusion":[158],"module":[159],"selective":[161],"cross-modal":[162],"fusion.":[163],"Extensive":[164],"experiments":[165],"four":[167],"MIE":[168],"datasets":[169],"demonstrate":[170],"our":[172],"method":[173],"significantly":[174],"outperforms":[175],"state-of-the-art":[177],"methods.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}