{"id":"https://openalex.org/W4415536694","doi":"https://doi.org/10.1145/3746027.3755397","title":"U-MERE: Unconstrained Multimodal Entity and Relation Extraction with Collaborative Modeling and Order-Sensitive Optimization","display_name":"U-MERE: Unconstrained Multimodal Entity and Relation Extraction with Collaborative Modeling and Order-Sensitive Optimization","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536694","doi":"https://doi.org/10.1145/3746027.3755397"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755397","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755397","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755397","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110805883","display_name":"Jia Wei","orcid":"https://orcid.org/0009-0007-5752-2132"},"institutions":[{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Jia","raw_affiliation_strings":["Key Laboratory of Target Cognition and Application Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China and School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-5752-2132","affiliations":[{"raw_affiliation_string":"Key Laboratory of Target Cognition and Application Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China and School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210137199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100783142","display_name":"Li Jin","orcid":"https://orcid.org/0000-0001-8833-4862"},"institutions":[{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Jin","raw_affiliation_strings":["Key Laboratory of Target Cognition and Application Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8833-4862","affiliations":[{"raw_affiliation_string":"Key Laboratory of Target Cognition and Application Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210137199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068039769","display_name":"Kaiwen Wei","orcid":"https://orcid.org/0000-0002-5830-0802"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiwen Wei","raw_affiliation_strings":["College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-5830-0802","affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107941655","display_name":"Y. Shang","orcid":"https://orcid.org/0009-0006-8052-2918"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuying Shang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-8052-2918","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018985705","display_name":"Nayu Liu","orcid":"https://orcid.org/0000-0002-7664-9856"},"institutions":[{"id":"https://openalex.org/I198091727","display_name":"Tiangong University","ror":"https://ror.org/00xsr9m91","country_code":"CN","type":"education","lineage":["https://openalex.org/I198091727"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nayu Liu","raw_affiliation_strings":["School of Computer Science and Technology, Tiangong University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-7664-9856","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tiangong University, Tianjin, China","institution_ids":["https://openalex.org/I198091727"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001032176","display_name":"Zhicong Lu","orcid":"https://orcid.org/0009-0005-7520-7799"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhicong Lu","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-7520-7799","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345183","display_name":"Qing Liu","orcid":"https://orcid.org/0000-0002-0592-171X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Liu","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0592-171X","affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210137199","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034890735","display_name":"Linlin Zhang","orcid":"https://orcid.org/0000-0002-2631-0555"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linhao Zhang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2631-0555","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072739941","display_name":"Jiang Zhong","orcid":"https://orcid.org/0000-0002-5169-4634"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang Zhong","raw_affiliation_strings":["College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-5169-4634","affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101567347","display_name":"Yanfeng Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanfeng Hu","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0119-126X","affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210137199","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4349","last_page":"4358"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.996999979019165,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996999979019165,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9550999999046326,"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/relationship-extraction","display_name":"Relationship extraction","score":0.7644000053405762},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.722000002861023},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.652899980545044},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6215999722480774},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6003999710083008},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5802000164985657},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.557200014591217},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4936000108718872},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44130000472068787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8384000062942505},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.7644000053405762},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.722000002861023},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.652899980545044},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6215999722480774},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6003999710083008},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5802000164985657},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.557200014591217},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5095000267028809},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4936000108718872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4560999870300293},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4546999931335449},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44130000472068787},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.35350000858306885},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2628999948501587},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755397","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755397","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1145/3746027.3755397","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755397","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2316640404","display_name":null,"funder_award_id":"62206267","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":4,"referenced_works":["https://openalex.org/W4385567363","https://openalex.org/W4401691645","https://openalex.org/W4403758869","https://openalex.org/W4404782322"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"multimodal":[1],"entity":[2,13,82,99],"and":[3,20,47,56,59,85,105,119,143,201,206],"relation":[4,83,127,148],"extraction":[5],"tasks":[6],"primarily":[7],"focus":[8],"on":[9,182],"text-to-text":[10],"or":[11],"text-to-visual":[12],"relations,":[14,100],"overlooking":[15],"real-world":[16],"complexities":[17],"involving":[18],"visual-to-text":[19],"visual-to-visual":[21],"cases,":[22],"thus":[23],"failing":[24],"to":[25,115,133,139,150,164],"capture":[26,140],"the":[27,37,90],"richer":[28],"semantic":[29],"structures":[30],"in":[31,211],"complex":[32],"cross-modal":[33,81,98],"interactions.":[34],"To":[35,65],"address":[36],"limitations,":[38],"we":[39,68,101,155],"propose":[40],"a":[41,71,157],"new":[42],"task,":[43],"Unconstrained":[44],"Multimodal":[45,158],"Entity":[46],"Relation":[48],"Extraction":[49],"(U-MERE),":[50],"which":[51,108],"jointly":[52,93,144],"extracts":[53],"arbitrary":[54],"visual":[55],"textual":[57],"entities,":[58,136],"their":[60],"relations":[61],"from":[62,124],"image-text":[63],"pairs.":[64],"accomplish":[66],"U-MERE,":[67,183],"construct":[69],"UMERE-Bench,":[70],"benchmark":[72],"with":[73,167],"over":[74],"9,000":[75],"samples":[76],"that":[77,176],"comprehensively":[78],"covers":[79],"four":[80],"directions":[84,96],"three":[86],"task":[87,117],"settings.":[88],"Given":[89],"difficulty":[91],"of":[92,97],"modeling":[94],"diverse":[95],"introduce":[102],"Collaborative":[103],"Modeling":[104],"Order-Sensitive":[106],"(CMOS),":[107],"collaboratively":[109],"guides":[110],"large":[111],"vision-language":[112],"models":[113,132],"(LVLMs)":[114],"decompose":[116],"complexity":[118],"mitigates":[120],"generation":[121],"order":[122,152],"bias":[123],"fixed":[125],"target":[126],"sequences.":[128],"CMOS":[129,189],"employs":[130],"small":[131],"generate":[134],"candidate":[135],"guiding":[137],"LVLMs":[138,178],"key":[141],"information":[142],"optimizes":[145],"multiple":[146,195],"feasible":[147],"orderings":[149],"reduce":[151],"dependency.":[153],"Additionally,":[154],"design":[156],"Order-aware":[159],"Matching":[160],"(MOM)":[161],"evaluation":[162],"method":[163],"align":[165],"predictions":[166],"ground":[168],"truth":[169],"for":[170],"precise":[171],"assessment.":[172],"Experimental":[173],"results":[174],"reveal":[175],"current":[177],"show":[179],"limited":[180],"performance":[181,193],"underscoring":[184],"its":[185,199],"inherent":[186],"challenges,":[187],"while":[188],"consistently":[190],"achieves":[191],"superior":[192],"across":[194],"advanced":[196],"LVLMs,":[197],"demonstrating":[198],"effectiveness":[200],"generalization":[202],"capability.":[203],"The":[204],"dataset":[205],"code":[207],"will":[208],"be":[209],"available":[210],"https://github.com/jiaweidoris/U-MERE.":[212]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}