{"id":"https://openalex.org/W4387969106","doi":"https://doi.org/10.1145/3581783.3612095","title":"Learning Implicit Entity-object Relations by Bidirectional Generative Alignment for Multimodal NER","display_name":"Learning Implicit Entity-object Relations by Bidirectional Generative Alignment for Multimodal NER","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969106","doi":"https://doi.org/10.1145/3581783.3612095"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612095","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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":"https://openalex.org/A5017636354","display_name":"Feng Chen","orcid":"https://orcid.org/0000-0003-1800-8441"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Feng Chen","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060310537","display_name":"Jiajia Liu","orcid":"https://orcid.org/0000-0003-3020-2677"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiajia Liu","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000713513","display_name":"Kaixiang Ji","orcid":"https://orcid.org/0000-0002-4669-8622"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaixiang Ji","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102928963","display_name":"Ren Wang","orcid":"https://orcid.org/0000-0001-6076-4895"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang Ren","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103017580","display_name":"Jian Wang","orcid":"https://orcid.org/0000-0003-4144-1753"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Wang","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014922345","display_name":"Jingdong Chen","orcid":"https://orcid.org/0000-0002-1872-2592"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingdong Chen","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5017636354"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5763,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.86695366,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4555","last_page":"4563"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.998199999332428,"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/computer-science","display_name":"Computer science","score":0.852682888507843},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6334846615791321},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6213062405586243},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5806097984313965},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5730506181716919},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4825548529624939},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47418221831321716},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4730716645717621},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4349311888217926},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4097638726234436}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.852682888507843},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6334846615791321},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6213062405586243},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5806097984313965},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5730506181716919},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4825548529624939},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47418221831321716},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4730716645717621},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4349311888217926},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4097638726234436},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612095","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1965555277","https://openalex.org/W2008830554","https://openalex.org/W2296283641","https://openalex.org/W2788647998","https://openalex.org/W2798298921","https://openalex.org/W3035259209","https://openalex.org/W3127151332","https://openalex.org/W3176858586","https://openalex.org/W3189857991","https://openalex.org/W4293518017","https://openalex.org/W4304091743","https://openalex.org/W6600561556","https://openalex.org/W6600577311"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559","https://openalex.org/W4299831724","https://openalex.org/W4283803360"],"abstract_inverted_index":{"The":[0],"challenge":[1],"posed":[2],"by":[3],"multimodal":[4],"named":[5,58],"entity":[6,25],"recognition":[7],"(MNER)":[8],"is":[9,116],"mainly":[10],"two-fold:":[11],"(1)":[12],"bridging":[13],"the":[14,24,37,43,83,90,120],"semantic":[15],"gap":[16],"between":[17],"text":[18],"and":[19,21,69,97],"image":[20,139],"(2)":[22],"matching":[23],"with":[26,72],"its":[27],"associated":[28],"object":[29],"in":[30,77],"image.":[31],"Existing":[32],"methods":[33],"fail":[34],"to":[35,42,60,74,88,118],"capture":[36],"implicit":[38,91],"entity-object":[39,92],"relations,":[40],"due":[41],"lack":[44],"of":[45,67],"corresponding":[46],"annotation.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51],"propose":[52],"a":[53],"bidirectional":[54,84],"generative":[55],"alignment":[56],"method":[57,134],"BGA-MNER":[59,65],"tackle":[61],"these":[62],"issues.":[63],"Our":[64],"consists":[66],"image2text":[68],"text2image":[70],"generation":[71],"respect":[73],"entity-salient":[75],"content":[76,123],"two":[78,129],"modalities.":[79],"It":[80],"jointly":[81],"optimizes":[82],"reconstruction":[85],"objectives,":[86],"leading":[87],"aligning":[89],"relations":[93],"under":[94],"such":[95],"direct":[96],"powerful":[98],"constraints.":[99],"Furthermore,":[100],"image-text":[101],"pairs":[102],"usually":[103],"contain":[104],"unmatched":[105],"components":[106],"which":[107],"are":[108],"noisy":[109],"for":[110,124],"generation.":[111,125],"A":[112],"stage-refined":[113],"context":[114],"sampler":[115],"proposed":[117],"extract":[119],"matched":[121],"cross-modal":[122],"Extensive":[126],"experiments":[127],"on":[128],"benchmarks":[130],"demonstrate":[131],"that":[132],"our":[133],"achieves":[135],"state-of-the-art":[136],"performance":[137],"without":[138],"input":[140],"during":[141],"inference.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}