{"id":"https://openalex.org/W4415540950","doi":"https://doi.org/10.1145/3746027.3755279","title":"ReMeREC: Relation-aware and Multi-entity Referring Expression Comprehension","display_name":"ReMeREC: Relation-aware and Multi-entity Referring Expression Comprehension","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540950","doi":"https://doi.org/10.1145/3746027.3755279"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755279","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755279","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":null,"display_name":"Yizhi Hu","orcid":"https://orcid.org/0009-0003-4538-3842"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhi Hu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-4538-3842","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112608678","display_name":"Zezhao Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zezhao Tian","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-0605-3867","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026841385","display_name":"Xingqun Qi","orcid":"https://orcid.org/0000-0002-9772-5707"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingqun Qi","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9772-5707","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039483325","display_name":"Su Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Su","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-8689-4521","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113034289","display_name":"Bingkun Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingkun Yang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-3704-8037","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025743346","display_name":"Junhui Yin","orcid":"https://orcid.org/0000-0001-8469-0472"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhui Yin","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8469-0472","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084960489","display_name":"Muyi Sun","orcid":"https://orcid.org/0000-0001-9506-7643"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Muyi Sun","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9506-7643","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353089","display_name":"Man Zhang","orcid":"https://orcid.org/0000-0003-3043-2122"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Man Zhang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3043-2122","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055505703","display_name":"Zhenan Sun","orcid":"https://orcid.org/0000-0003-4029-9935"},"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenan Sun","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4029-9935","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26225948,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4010","last_page":"4019"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9979000091552734,"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/ambiguity","display_name":"Ambiguity","score":0.6516000032424927},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4975000023841858},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.4634999930858612},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4496000111103058},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4465999901294708},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.43389999866485596},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.42250001430511475},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.36809998750686646},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.36320000886917114}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.770799994468689},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7290999889373779},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6516000032424927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6395000219345093},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4975000023841858},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.4634999930858612},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4496000111103058},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4465999901294708},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.43389999866485596},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.42250001430511475},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C9616225","wikidata":"https://www.wikidata.org/wiki/Q3929429","display_name":"Semantic reasoner","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C193125573","wikidata":"https://www.wikidata.org/wiki/Q7449065","display_name":"Semantic interpretation","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C47385372","wikidata":"https://www.wikidata.org/wiki/Q7098943","display_name":"Optimal distinctiveness theory","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33230000734329224},{"id":"https://openalex.org/C78022038","wikidata":"https://www.wikidata.org/wiki/Q7644082","display_name":"Superordinate goals","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29260000586509705},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.273499995470047},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.2581999897956848},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25110000371932983},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755279","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755279","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/G5481784229","display_name":null,"funder_award_id":"62306309?62406037?U23B2054?62276263","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":25,"referenced_works":["https://openalex.org/W2489434015","https://openalex.org/W2946086442","https://openalex.org/W2947312908","https://openalex.org/W2952524542","https://openalex.org/W2963109634","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W2984121207","https://openalex.org/W2986755220","https://openalex.org/W2987734933","https://openalex.org/W3034772468","https://openalex.org/W3035097537","https://openalex.org/W3110435696","https://openalex.org/W3138516171","https://openalex.org/W3192448690","https://openalex.org/W4214490042","https://openalex.org/W4312446817","https://openalex.org/W4313145013","https://openalex.org/W4382458695","https://openalex.org/W4386065815","https://openalex.org/W4386076142","https://openalex.org/W4386076636","https://openalex.org/W4387272106","https://openalex.org/W4387623721","https://openalex.org/W4402716383"],"related_works":[],"abstract_inverted_index":{"Referring":[0],"Expression":[1],"Comprehension":[2],"(REC)":[3],"aims":[4],"to":[5,16,44,103,112,173,180,190,207],"localize":[6,104],"specified":[7],"entities":[8,106,148],"or":[9],"regions":[10],"from":[11,118,149],"the":[12,17,31,51,114,119,126,143,159,168,186,193,225,236],"source":[13,127],"image":[14],"according":[15],"given":[18],"natural":[19,128],"language":[20,129],"descriptions.":[21],"While":[22],"existing":[23],"methods":[24],"enable":[25],"single-entity":[26],"localization,":[27],"they":[28],"overlook":[29],"modeling":[30],"complex":[32,251],"inter-entity":[33],"relationship":[34,177,252],"in":[35,125,247],"more":[36,182],"practical":[37],"multi-entity":[38,55,78,248],"scenes,":[39],"which":[40,215],"limits":[41,64],"their":[42,109],"ability":[43],"produce":[45],"accurate":[46],"and":[47,59,84,100,145,202,222,250],"reliable":[48],"results.":[49],"Moreover,":[50],"lack":[52],"of":[53,121,147,162,185,239],"high-quality":[54],"datasets":[56,234],"incorporating":[57],"fine-grained":[58,82,151,194],"paired":[60],"image-text-relation":[61],"annotations":[62],"also":[63],"addressing":[65],"this":[66,70],"challenge.":[67],"To":[68],"achieve":[69],"task,":[71],"we":[72,90,131,166,204],"first":[73],"manually":[74],"construct":[75],"a":[76,93,133,181,209,258],"relation-aware":[77],"REC":[79],"dataset":[80],"with":[81],"relation":[83],"text":[85,152],"annotations,":[86],"namely":[87],"ReMeX.":[88],"Additionally,":[89],"propose":[91],"ReMeREC,":[92],"novel":[94,134],"framework":[95],"that":[96,157],"effectively":[97],"integrates":[98],"textual":[99,211,226],"visual":[101],"cues":[102],"multiple":[105,199],"while":[107],"capturing":[108],"inter-relationship.":[110],"Specifically,":[111],"mitigate":[113],"semantic":[115,175],"ambiguity":[116],"arising":[117],"absence":[120],"explicit":[122],"entity":[123,200],"boundaries":[124,201],"description,":[130],"introduce":[132],"Text-adaptive":[135],"Multi-entity":[136],"Perceptron":[137],"(TMP).":[138],"TMP":[139],"dynamically":[140],"infers":[141],"both":[142],"quantity":[144],"span":[146],"corresponding":[150],"cues,":[153],"thus":[154],"deriving":[155],"representations":[156],"preserve":[158],"unique":[160],"characteristics":[161],"each":[163],"entity.":[164],"Meanwhile,":[165],"design":[167],"Entity":[169],"Inter-relationship":[170],"Reasoner":[171],"(EIR)":[172],"enhance":[174],"distinctiveness":[176],"modeling,":[178],"leading":[179],"profound":[183],"perception":[184],"global":[187],"scene.":[188],"Furthermore,":[189],"better":[191],"capture":[192],"linguistic":[195],"prompts":[196],"for":[197],"delineating":[198],"inter-relationship,":[203],"leverage":[205],"LLMs":[206],"generate":[208],"small-scale":[210],"dataset,":[212],"dubbed":[213],"EntityText,":[214],"serves":[216],"as":[217],"an":[218],"effective":[219],"auxiliary":[220],"resource":[221],"further":[223],"improves":[224],"understanding.":[227],"Extensive":[228],"experiments":[229],"conducted":[230],"on":[231],"four":[232],"benchmark":[233],"demonstrate":[235],"superior":[237],"performance":[238],"our":[240],"framework.":[241],"Remarkably,":[242],"ReMeREC":[243],"achieves":[244],"outstanding":[245],"results":[246],"grounding":[249],"prediction,":[253],"outperforming":[254],"other":[255],"counterparts":[256],"by":[257],"large":[259],"margin.":[260]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-25T00:00:00"}