{"id":"https://openalex.org/W4285594363","doi":"https://doi.org/10.1145/3548688","title":"Referring Expression Comprehension Via Enhanced Cross-modal Graph Attention Networks","display_name":"Referring Expression Comprehension Via Enhanced Cross-modal Graph Attention Networks","publication_year":2022,"publication_date":"2022-07-15","ids":{"openalex":"https://openalex.org/W4285594363","doi":"https://doi.org/10.1145/3548688"},"language":"en","primary_location":{"id":"doi:10.1145/3548688","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3548688","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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/A5100404631","display_name":"Jia Wang","orcid":"https://orcid.org/0000-0002-0998-251X"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Jia Wang","raw_affiliation_strings":["National Yang Ming Chiao Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030523554","display_name":"Jingcheng Ke","orcid":"https://orcid.org/0000-0002-2262-6261"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jingcheng Ke","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040050806","display_name":"Hong-Han Shuai","orcid":"https://orcid.org/0000-0003-2216-077X"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hong-Han Shuai","raw_affiliation_strings":["National Yang Ming Chiao Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048205934","display_name":"Yung\u2010Hui Li","orcid":"https://orcid.org/0000-0002-0475-3689"},"institutions":[{"id":"https://openalex.org/I4210113837","display_name":"Taiwan Forestry Research Institute","ror":"https://ror.org/01d34a364","country_code":"TW","type":"facility","lineage":["https://openalex.org/I26359584","https://openalex.org/I4210113837"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yung-Hui Li","raw_affiliation_strings":["Hon Hai Research Institute, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Hon Hai Research Institute, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I4210113837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000780442","display_name":"Wen-Huang Cheng","orcid":"https://orcid.org/0000-0002-4662-7875"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wen-Huang Cheng","raw_affiliation_strings":["National Yang Ming Chiao Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100404631"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":1.732,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.8576352,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"19","issue":"2","first_page":"1","last_page":"21"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9965000152587891,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9783999919891357,"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/comprehension","display_name":"Comprehension","score":0.8176583647727966},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7273052930831909},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.7188774347305298},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5920544862747192},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5748313665390015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5491259098052979},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5154401063919067},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5002541542053223},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4870167374610901},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4704127609729767},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42087966203689575},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2201073169708252},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11782699823379517},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.061072349548339844}],"concepts":[{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.8176583647727966},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7273052930831909},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.7188774347305298},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5920544862747192},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5748313665390015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5491259098052979},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5154401063919067},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5002541542053223},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4870167374610901},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4704127609729767},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42087966203689575},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2201073169708252},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11782699823379517},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.061072349548339844},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3548688","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3548688","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6499999761581421}],"awards":[{"id":"https://openalex.org/G2374886573","display_name":null,"funder_award_id":"MOST-109-2223-E-009-002-MY3, MOST-110-2218-E-A49-018, and MOST-111-2634-F-007-002","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2064675550","https://openalex.org/W2109586012","https://openalex.org/W2123442489","https://openalex.org/W2165227743","https://openalex.org/W2251630646","https://openalex.org/W2277195237","https://openalex.org/W2288122362","https://openalex.org/W2564871695","https://openalex.org/W2571175805","https://openalex.org/W2583360688","https://openalex.org/W2609144136","https://openalex.org/W2740509411","https://openalex.org/W2754689878","https://openalex.org/W2770129969","https://openalex.org/W2774419718","https://openalex.org/W2779827764","https://openalex.org/W2784458614","https://openalex.org/W2799263800","https://openalex.org/W2885156408","https://openalex.org/W2885195348","https://openalex.org/W2886970679","https://openalex.org/W2919570819","https://openalex.org/W2930957955","https://openalex.org/W2952524542","https://openalex.org/W2955088691","https://openalex.org/W2962764817","https://openalex.org/W2963109634","https://openalex.org/W2963735856","https://openalex.org/W2964345792","https://openalex.org/W2969897437","https://openalex.org/W2986755220","https://openalex.org/W2990138404","https://openalex.org/W2997383919","https://openalex.org/W3014509131","https://openalex.org/W3034772468","https://openalex.org/W3038528491","https://openalex.org/W3041730883","https://openalex.org/W3043436549","https://openalex.org/W3048749423","https://openalex.org/W3092956019","https://openalex.org/W3093017735","https://openalex.org/W3111077383","https://openalex.org/W3112195279","https://openalex.org/W3120524222","https://openalex.org/W3124959131","https://openalex.org/W3128307553","https://openalex.org/W3138716232","https://openalex.org/W3154503495","https://openalex.org/W3167267673","https://openalex.org/W3175016299","https://openalex.org/W3187240237","https://openalex.org/W3192668118","https://openalex.org/W3202403972","https://openalex.org/W3204228395","https://openalex.org/W3207798279","https://openalex.org/W3212847756","https://openalex.org/W3214094165","https://openalex.org/W4200474188","https://openalex.org/W4300058068","https://openalex.org/W6750703656"],"related_works":["https://openalex.org/W2329500892","https://openalex.org/W28991112","https://openalex.org/W2370726991","https://openalex.org/W2369710579","https://openalex.org/W2545348020","https://openalex.org/W4327728159","https://openalex.org/W2912751582","https://openalex.org/W2130893381","https://openalex.org/W2373862202","https://openalex.org/W2388232445"],"abstract_inverted_index":{"Referring":[0],"expression":[1,50,56,64,98,106,129,167],"comprehension":[2,65,168],"aims":[3],"to":[4,13,22,42,57,148,187],"localize":[5],"a":[6,14,48,101,115],"specific":[7],"object":[8,74],"in":[9,33,62,85,151],"an":[10,58,135,138],"image":[11],"according":[12],"given":[15,49],"language":[16,88],"description.":[17,89],"It":[18],"is":[19,66,77,146,185],"still":[20],"challenging":[21],"comprehend":[23],"and":[24,36,51,130],"mitigate":[25],"the":[26,34,44,53,67,81,86,91,97,125,128,131,153,159],"gap":[27],"between":[28,127],"various":[29],"types":[30],"of":[31,55,69,83,134,155,191],"information":[32],"visual":[35],"textual":[37],"domains.":[38],"Generally,":[39],"it":[40],"needs":[41],"extract":[43],"salient":[45],"features":[46,54],"from":[47],"match":[52],"image.":[59,136],"One":[60],"challenge":[61],"referring":[63,105,166],"number":[68,82],"region":[70],"proposals":[71],"generated":[72],"by":[73,96],"detection":[75],"methods":[76],"far":[78],"more":[79],"than":[80,179],"entities":[84],"corresponding":[87],"Remarkably,":[90],"candidate":[92],"regions":[93],"without":[94],"described":[95],"will":[99],"bring":[100],"severe":[102],"impact":[103],"on":[104,158,163],"comprehension.":[107],"To":[108],"tackle":[109],"this":[110],"problem,":[111],"we":[112],"first":[113],"propose":[114],"novel":[116],"Enhanced":[117],"Cross-modal":[118],"Graph":[119,142],"Attention":[120],"Networks":[121],"(ECMGANs)":[122],"that":[123,172],"boosts":[124],"matching":[126,193],"entity":[132],"position":[133],"Then,":[137],"effective":[139],"strategy":[140],"named":[141],"Node":[143],"Erase":[144],"(GNE)":[145],"proposed":[147],"assist":[149],"ECMGANs":[150,174],"eliminating":[152],"effect":[154],"irrelevant":[156],"objects":[157],"target":[160],"object.":[161],"Experiments":[162],"three":[164],"public":[165],"datasets":[169],"show":[170],"unambiguously":[171],"our":[173],"framework":[175],"achieves":[176],"better":[177],"performance":[178],"other":[180],"state-of-the-art":[181],"methods.":[182],"Moreover,":[183],"GNE":[184],"able":[186],"obtain":[188],"higher":[189],"accuracies":[190],"visual-expression":[192],"effectively.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}