{"id":"https://openalex.org/W4205816704","doi":"https://doi.org/10.1145/3469877.3490592","title":"Entity Relation Fusion for Real-Time One-Stage Referring Expression Comprehension","display_name":"Entity Relation Fusion for Real-Time One-Stage Referring Expression Comprehension","publication_year":2021,"publication_date":"2021-12-01","ids":{"openalex":"https://openalex.org/W4205816704","doi":"https://doi.org/10.1145/3469877.3490592"},"language":"en","primary_location":{"id":"doi:10.1145/3469877.3490592","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3469877.3490592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100432192","display_name":"Hang Yu","orcid":"https://orcid.org/0009-0000-4624-1123"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Yu","raw_affiliation_strings":["Beihang University, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, CN","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100662467","display_name":"Weixin Li","orcid":"https://orcid.org/0000-0002-5093-5635"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixin Li","raw_affiliation_strings":["Beihang University, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, CN","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001470290","display_name":"Jiankai Li","orcid":"https://orcid.org/0009-0008-8858-7980"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiankai Li","raw_affiliation_strings":["Beihang University, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, CN","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100783342","display_name":"Ye Du","orcid":"https://orcid.org/0000-0002-3057-1862"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Du","raw_affiliation_strings":["Beihang University, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, CN","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"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":"1","last_page":"8"},"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":0.9947999715805054,"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":0.9927999973297119,"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":0.7605056762695312},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6964399814605713},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6814361810684204},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.6681259870529175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6615911722183228},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.652267336845398},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5020773410797119},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.4796169698238373},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45083722472190857},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3761807978153229},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2731362581253052},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10000348091125488},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09371042251586914},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09361287951469421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7605056762695312},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6964399814605713},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6814361810684204},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.6681259870529175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6615911722183228},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.652267336845398},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5020773410797119},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.4796169698238373},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45083722472190857},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3761807978153229},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2731362581253052},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10000348091125488},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09371042251586914},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09361287951469421},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3469877.3490592","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3469877.3490592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2251512949","https://openalex.org/W2571175805","https://openalex.org/W2799263800","https://openalex.org/W2896457183","https://openalex.org/W2904910963","https://openalex.org/W2965597639","https://openalex.org/W2981575209","https://openalex.org/W2981985547","https://openalex.org/W2982210816","https://openalex.org/W2984121207","https://openalex.org/W2987734933","https://openalex.org/W3023463084","https://openalex.org/W3034772468","https://openalex.org/W3037533539","https://openalex.org/W3103651098","https://openalex.org/W3110435696","https://openalex.org/W4241886172"],"related_works":["https://openalex.org/W4249847449","https://openalex.org/W44395729","https://openalex.org/W2765338038","https://openalex.org/W1496225612","https://openalex.org/W1523500768","https://openalex.org/W1566843515","https://openalex.org/W4292850564","https://openalex.org/W4206776094","https://openalex.org/W3154920669","https://openalex.org/W3121197456"],"abstract_inverted_index":{"Referring":[0],"Expression":[1],"Comprehension":[2],"(REC)":[3],"is":[4,11,41,209],"the":[5,14,30,44,52,65,83,102,143,174,179,184,200,212],"task":[6],"of":[7,48,122,145,147],"grounding":[8,34,58,123],"object":[9,72,111,186,195],"which":[10,55],"referred":[12,110,180],"by":[13,112],"language":[15,25,53,140,175],"expression.":[16],"Previous":[17],"one-stage":[18,98,214],"REC":[19,99,217],"methods":[20,62],"usually":[21],"use":[22,64],"one":[23,153],"single":[24],"feature":[26,66,73,79,154,182,187,196],"vector":[27],"to":[28,108,138,141,177,193],"represent":[29],"whole":[31],"query":[32],"for":[33,69],"and":[35,189,215,219],"no":[36],"reasoning":[37,115],"between":[38,85,158],"different":[39,78,88,117,150,159],"objects":[40,49,86,124,148],"performed":[42],"despite":[43],"rich":[45],"relation":[46,113],"cues":[47],"contained":[50],"in":[51,173,183,224],"expression,":[54],"depresses":[56],"their":[57],"accuracy.":[59],"Additionally,":[60],"these":[61,92],"mostly":[63],"pyramid":[67],"networks":[68],"multi-scale":[70],"visual":[71,185],"extraction":[74],"but":[75],"ground":[76],"on":[77,116,199],"layers":[80],"separately,":[81,128],"neglecting":[82],"connections":[84,157],"with":[87,149,211],"scales.":[89],"To":[90],"address":[91],"problems,":[93],"we":[94,129,161],"propose":[95,130],"a":[96,131,163],"novel":[97],"method,":[100],"i.e.":[101],"Entity":[103],"Relation":[104,164],"Fusion":[105,135,167],"Network":[106],"(ERFN)":[107],"locate":[109],"guided":[114],"objects.":[118],"In":[119],"ERFN,":[120],"instead":[121],"at":[125],"each":[126],"layer":[127],"Language":[132],"Guided":[133,165],"Multi-Scale":[134],"(LGMSF)":[136],"model":[137,169],"utilize":[139],"guide":[142,194],"fusion":[144,197],"representations":[146],"scales":[151],"into":[152],"map.For":[155],"modeling":[156],"objects,":[160],"design":[162],"Feature":[166],"(RGFF)":[168],"that":[170,206],"extracts":[171,191],"entities":[172],"expression":[176],"enhance":[178],"entity":[181],"map,":[188],"further":[190],"relations":[192],"based":[198],"self-attention":[201],"mechanism.":[202],"Experimental":[203],"results":[204],"show":[205],"our":[207],"method":[208],"competitive":[210],"state-of-the-art":[213],"two-stage":[216],"methods,":[218],"can":[220],"also":[221],"keep":[222],"inferring":[223],"real":[225],"time.":[226]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}