{"id":"https://openalex.org/W4391837206","doi":"https://doi.org/10.1145/3648370","title":"Region-Focused Network for Dense Captioning","display_name":"Region-Focused Network for Dense Captioning","publication_year":2024,"publication_date":"2024-02-15","ids":{"openalex":"https://openalex.org/W4391837206","doi":"https://doi.org/10.1145/3648370"},"language":"en","primary_location":{"id":"doi:10.1145/3648370","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3648370","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/A5061381102","display_name":"Qingbao Huang","orcid":"https://orcid.org/0000-0001-7691-347X"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qingbao Huang","raw_affiliation_strings":["Guangxi University, Nanning, China"],"affiliations":[{"raw_affiliation_string":"Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033158939","display_name":"Pijian Li","orcid":"https://orcid.org/0009-0005-1924-5248"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pijian Li","raw_affiliation_strings":["Guangxi University, Nanning, China"],"affiliations":[{"raw_affiliation_string":"Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102026291","display_name":"Youji Huang","orcid":"https://orcid.org/0009-0005-8392-2047"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youji Huang","raw_affiliation_strings":["Guangxi University, Nanning, China"],"affiliations":[{"raw_affiliation_string":"Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062793914","display_name":"Feng Shuang","orcid":"https://orcid.org/0000-0002-4733-4732"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Shuang","raw_affiliation_strings":["Guangxi University, Nanning, China and Guangxi Key Laboratory of Intelligent Control and Maintenance of Power Equipment, Nanning, China"],"affiliations":[{"raw_affiliation_string":"Guangxi University, Nanning, China and Guangxi Key Laboratory of Intelligent Control and Maintenance of Power Equipment, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"last","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 Dat 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 Dat and Intelligent Robot (SCUT), Ministry of Education, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5061381102"],"corresponding_institution_ids":["https://openalex.org/I150807315"],"apc_list":null,"apc_paid":null,"fwci":0.9971,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.747517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"20","issue":"6","first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9897000193595886,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9886999726295471,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7977067232131958},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4534086287021637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20145952701568604}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7977067232131958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4534086287021637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20145952701568604},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3648370","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3648370","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":[{"display_name":"Reduced inequalities","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1380176761","display_name":null,"funder_award_id":"2020B0101100002","funder_id":"https://openalex.org/F4320323059","funder_display_name":"South China University of Technology"},{"id":"https://openalex.org/G1473307615","display_name":null,"funder_award_id":"2022GXNSFAA035627","funder_id":"https://openalex.org/F4320322768","funder_display_name":"Natural Science Foundation of Guangxi Province"},{"id":"https://openalex.org/G1477544716","display_name":null,"funder_award_id":"Guangdong","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2376276132","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4572242254","display_name":null,"funder_award_id":"2020B0101100002","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G4913122426","display_name":null,"funder_award_id":"2020B0101100002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5760752404","display_name":null,"funder_award_id":"Projects","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6770297356","display_name":null,"funder_award_id":"62276072","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7020966827","display_name":null,"funder_award_id":"62076100","funder_id":"https://openalex.org/F4320323059","funder_display_name":"South China University of Technology"},{"id":"https://openalex.org/G7608752429","display_name":null,"funder_award_id":"Talent","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8189774080","display_name":null,"funder_award_id":"62076100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8586639432","display_name":null,"funder_award_id":"62076100","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322768","display_name":"Natural Science Foundation of Guangxi Province","ror":null},{"id":"https://openalex.org/F4320323059","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320337368","display_name":"Division of Graduate Education","ror":"https://ror.org/00whkrf32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W2050482109","https://openalex.org/W2277195237","https://openalex.org/W2481240925","https://openalex.org/W2552002300","https://openalex.org/W2559655401","https://openalex.org/W2561296180","https://openalex.org/W2607662938","https://openalex.org/W2612690371","https://openalex.org/W2745461083","https://openalex.org/W2776346076","https://openalex.org/W2788710361","https://openalex.org/W2903617461","https://openalex.org/W2914163459","https://openalex.org/W2963101956","https://openalex.org/W2963536419","https://openalex.org/W2963683498","https://openalex.org/W2963758027","https://openalex.org/W2975503096","https://openalex.org/W2986670728","https://openalex.org/W2986823309","https://openalex.org/W2997547717","https://openalex.org/W2999905431","https://openalex.org/W3006871679","https://openalex.org/W3034655362","https://openalex.org/W3034787499","https://openalex.org/W3035365026","https://openalex.org/W3035520612","https://openalex.org/W3038593179","https://openalex.org/W3082436432","https://openalex.org/W3096609285","https://openalex.org/W3096612875","https://openalex.org/W3107848485","https://openalex.org/W3111947517","https://openalex.org/W3124043039","https://openalex.org/W3128560592","https://openalex.org/W3129130152","https://openalex.org/W3136792391","https://openalex.org/W3159583533","https://openalex.org/W3162954998","https://openalex.org/W3174377922","https://openalex.org/W3177525997","https://openalex.org/W3194397797","https://openalex.org/W3195680250","https://openalex.org/W3205607545","https://openalex.org/W3205765769","https://openalex.org/W3206617243","https://openalex.org/W3211865849","https://openalex.org/W4200301490","https://openalex.org/W4205357838","https://openalex.org/W4206982465","https://openalex.org/W4214946871","https://openalex.org/W4225512839","https://openalex.org/W4226280874","https://openalex.org/W4238846128","https://openalex.org/W4249009392","https://openalex.org/W4253959227","https://openalex.org/W4255556797","https://openalex.org/W4285280022","https://openalex.org/W4286696412","https://openalex.org/W4304080274","https://openalex.org/W4308785766","https://openalex.org/W4312245820","https://openalex.org/W4318953563","https://openalex.org/W6748308768"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403"],"abstract_inverted_index":{"Dense":[0],"captioning":[1],"is":[2,148,187],"a":[3,24,89,145],"very":[4],"critical":[5],"but":[6],"under-explored":[7],"task,":[8],"which":[9],"aims":[10],"to":[11,31,39,60,93,98,118,124,141,150],"densely":[12],"detect":[13],"localized":[14],"regions-of-interest":[15],"(RoIs)":[16],"and":[17,81,109,113,152,158,169],"describe":[18],"them":[19],"with":[20],"natural":[21],"language":[22],"in":[23,57,76],"given":[25],"image.":[26],"Although":[27],"recent":[28],"studies":[29],"tried":[30],"fuse":[32],"multi-scale":[33],"features":[34,70],"from":[35,48,128],"different":[36],"visual":[37,68],"instances":[38],"generate":[40,159],"more":[41],"accurate":[42],"descriptions,":[43],"their":[44],"methods":[45],"still":[46],"suffer":[47],"the":[49,101,106,111,120,126,132,137,142,154,160,178],"lack":[50],"of":[51,53],"exploration":[52],"relation":[54],"semantic":[55],"information":[56,130,140,157],"images,":[58,102],"leading":[59],"less":[61],"informative":[62],"descriptions.":[63,162],"Furthermore,":[64],"indiscriminately":[65],"fusing":[66],"all":[67],"instance":[69],"will":[71],"introduce":[72],"redundant":[73,129],"information,":[74],"resulting":[75],"poor":[77],"matching":[78],"between":[79,116],"descriptions":[80],"corresponding":[82,161],"regions.":[83],"In":[84],"this":[85],"work,":[86],"we":[87,103,135],"propose":[88],"Region-Focused":[90],"Network":[91],"(RFN)":[92],"address":[94],"these":[95],"issues.":[96],"Specifically,":[97],"fully":[99],"comprehend":[100],"first":[104],"extract":[105,136],"object-level":[107],"features,":[108],"encode":[110],"interaction":[112],"position":[114],"relations":[115],"objects":[117],"enhance":[119],"object":[121],"representations.":[122],"Then,":[123],"decrease":[125],"interference":[127],"about":[131],"target":[133],"region,":[134],"most":[138],"relevant":[139],"region.":[143],"Finally,":[144],"region-based":[146],"Transformer":[147],"employed":[149],"compose":[151],"align":[153],"previous":[155],"mined":[156],"Extensive":[163],"experiments":[164],"on":[165],"Visual":[166],"Genome":[167],"V1.0":[168],"V1.2":[170],"datasets":[171],"show":[172],"that":[173],"our":[174],"RFN":[175],"model":[176],"outperforms":[177],"state-of-the-art":[179],"methods,":[180],"thus":[181],"verifying":[182],"its":[183],"effectiveness.":[184],"Our":[185],"code":[186],"available":[188],"at":[189],"https://github.com/VILAN-Lab/DesCap":[190],".":[191]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}