{"id":"https://openalex.org/W4415536744","doi":"https://doi.org/10.1145/3746027.3755424","title":"Ground and Reconstruct: Entity-Region Bidirectional Alignment Pre-Training for Low-Resource GMNER","display_name":"Ground and Reconstruct: Entity-Region Bidirectional Alignment Pre-Training for Low-Resource GMNER","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536744","doi":"https://doi.org/10.1145/3746027.3755424"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755424","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd 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/A5033748003","display_name":"Runwei Situ","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Runwei Situ","raw_affiliation_strings":["South China University of Technology, Guangzhou, China and Key Laboratory of Big Data and Intelligent Robot (SCUT), Ministry of Education, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China and Key Laboratory of Big Data and Intelligent Robot (SCUT), Ministry of Education, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089123257","display_name":"Yi Cai","orcid":"https://orcid.org/0000-0002-1767-789X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Cai","raw_affiliation_strings":["South China University of Technology, Guangzhou, China and Key Laboratory of Big Data and Intelligent Robot (SCUT), Ministry of Education, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China and Key Laboratory of Big Data and Intelligent Robot (SCUT), Ministry of Education, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010277066","display_name":"Yong Xu","orcid":"https://orcid.org/0000-0001-7183-3155"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Xu","raw_affiliation_strings":["South China University of Technology, Guangzhou, China and Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China and Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002191673","display_name":"Jiexin Wang","orcid":"https://orcid.org/0000-0002-7064-6507"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiexin Wang","raw_affiliation_strings":["South China University of Technology, Guangzhou, China and Key Laboratory of Big Data and Intelligent Robot (SCUT), Ministry of Education, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China and Key Laboratory of Big Data and Intelligent Robot (SCUT), Ministry of Education, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033748003"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15986091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4418","last_page":"4426"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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/T10028","display_name":"Topic Modeling","score":0.9932000041007996,"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":0.9904000163078308,"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/generalization","display_name":"Generalization","score":0.625},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4392000138759613},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42969998717308044},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.3871000111103058},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.37369999289512634},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.36880001425743103},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3621000051498413},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.35839998722076416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922000288963318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6779000163078308},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.625},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4392000138759613},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4341999888420105},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.3871000111103058},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.36880001425743103},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3621000051498413},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3434999883174896},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3393999934196472},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25119999051094055},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755424","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G453967609","display_name":null,"funder_award_id":"62476097","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W3127151332"],"related_works":[],"abstract_inverted_index":{"Grounded":[0],"Multimodal":[1,7],"Named":[2,8],"Entity":[3,9],"Recognition":[4,10],"(GMNER)":[5],"extends":[6],"(MNER)":[11],"by":[12],"identifying":[13],"named":[14],"entities,":[15],"their":[16],"types,":[17],"and":[18,24,43,85,98,146,158],"corresponding":[19],"image":[20],"regions.":[21],"Fine-grained":[22],"MNER":[23],"Grounding":[25],"(FMNERG)":[26],"further":[27],"refines":[28],"entity":[29,96,103],"categorization.":[30],"However,":[31],"existing":[32,154],"methods":[33],"struggle":[34],"with":[35],"scarce":[36],"annotated":[37],"data,":[38,121],"particularly":[39],"in":[40,162],"low-resource":[41,155],"scenarios,":[42],"often":[44],"fail":[45],"to":[46,48,139],"generalize":[47],"unseen":[49,140],"entities.":[50,141],"While":[51],"vision-language":[52],"pre-training":[53,90,120],"(VLP)":[54],"leverages":[55],"unlabeled":[56,134],"image-caption":[57],"pairs,":[58,136],"it":[59],"primarily":[60],"learns":[61],"generic":[62],"visual-linguistic":[63],"representations,":[64],"overlooking":[65],"fine-grained":[66,109,118],"entity-region":[67,110],"alignment":[68],"crucial":[69],"for":[70,83,95,102,114],"entity-related":[71],"tasks.":[72],"To":[73,112],"address":[74],"these":[75],"challenges,":[76],"we":[77,122],"propose":[78],"a":[79],"unified":[80],"VLP":[81],"framework":[82,152],"GMNER":[84,145],"FMNERG,":[86],"introducing":[87],"two":[88],"task-specific":[89],"objectives:":[91],"Entity-to-Region":[92],"Alignment":[93,100],"(ETRA)":[94],"grounding":[97],"Region-to-Entity":[99],"(RTEA)":[101],"reconstruction.":[104],"These":[105],"tasks":[106],"jointly":[107],"optimize":[108],"alignment.":[111],"compensate":[113],"the":[115],"lack":[116],"of":[117],"multimodal":[119],"develop":[123],"an":[124],"automatic":[125],"labeling":[126],"method":[127],"that":[128,150],"distills":[129],"entity-oriented":[130],"knowledge":[131],"from":[132],"large-scale":[133],"image-text":[135],"enhancing":[137],"generalization":[138],"Extensive":[142],"experiments":[143],"on":[144],"FMNERG":[147],"benchmarks":[148],"demonstrate":[149],"our":[151],"outperforms":[153],"learning":[156],"approaches":[157],"achieves":[159],"competitive":[160],"performance":[161],"full-supervision,":[163],"underscoring":[164],"its":[165],"effectiveness":[166],"across":[167],"diverse":[168],"data":[169],"conditions.":[170]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-25T00:00:00"}