{"id":"https://openalex.org/W3205625102","doi":"https://doi.org/10.1109/tpami.2021.3119754","title":"Dense Relational Image Captioning via Multi-Task Triple-Stream Networks","display_name":"Dense Relational Image Captioning via Multi-Task Triple-Stream Networks","publication_year":2021,"publication_date":"2021-10-15","ids":{"openalex":"https://openalex.org/W3205625102","doi":"https://doi.org/10.1109/tpami.2021.3119754","mag":"3205625102","pmid":"https://pubmed.ncbi.nlm.nih.gov/34648432"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3119754","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.03855","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100393157","display_name":"Dong-Jin Kim","orcid":"https://orcid.org/0000-0001-7231-7494"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dong-Jin Kim","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078114111","display_name":"Tae-Hyun Oh","orcid":"https://orcid.org/0000-0003-0468-1571"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tae-Hyun Oh","raw_affiliation_strings":["Department of Electrical Engineering, Graduate School of AI (GSAI), Pohang University of Science and Technology, Pohang, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Graduate School of AI (GSAI), Pohang University of Science and Technology, Pohang, Republic of Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010273576","display_name":"Jinsoo Choi","orcid":"https://orcid.org/0000-0002-3650-9461"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinsoo Choi","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012455275","display_name":"In So Kweon","orcid":"https://orcid.org/0000-0001-9626-5983"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"In So Kweon","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.084,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.810715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"44","issue":"11","first_page":"7348","last_page":"7362"},"is_retracted":false,"is_paratext":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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9958,"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":0.9891,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9764433},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task Analysis","score":0.42459768}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9764433},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7865002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5799597},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5766812},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5217991},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5026622},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.493108},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.43060747},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.43039516},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.42459768},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.4133983},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3717289},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34054667},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.091878414},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3119754","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2010.03855","pdf_url":"https://arxiv.org/pdf/2010.03855","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34648432","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2010.03855","pdf_url":"https://arxiv.org/pdf/2010.03855","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"score":0.54,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":72,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W2049705550","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2117539524","https://openalex.org/W2125215748","https://openalex.org/W2133459682","https://openalex.org/W2143017621","https://openalex.org/W2159564241","https://openalex.org/W2169540047","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2302086703","https://openalex.org/W24089286","https://openalex.org/W2479423890","https://openalex.org/W2549599535","https://openalex.org/W2552002300","https://openalex.org/W2575842049","https://openalex.org/W2579549467","https://openalex.org/W2591644541","https://openalex.org/W2604178507","https://openalex.org/W2607855566","https://openalex.org/W2740962769","https://openalex.org/W2745461083","https://openalex.org/W2754191212","https://openalex.org/W2777602943","https://openalex.org/W2798959609","https://openalex.org/W2810482788","https://openalex.org/W2883104598","https://openalex.org/W2883170015","https://openalex.org/W2885013662","https://openalex.org/W2886970679","https://openalex.org/W2887029921","https://openalex.org/W2890531016","https://openalex.org/W2892245540","https://openalex.org/W2949197413","https://openalex.org/W2950096400","https://openalex.org/W2955988340","https://openalex.org/W2962716332","https://openalex.org/W2962737704","https://openalex.org/W2962811161","https://openalex.org/W2962844592","https://openalex.org/W2962968835","https://openalex.org/W2963084599","https://openalex.org/W2963088515","https://openalex.org/W2963091558","https://openalex.org/W2963097937","https://openalex.org/W2963224792","https://openalex.org/W2963536419","https://openalex.org/W2963649796","https://openalex.org/W2963650529","https://openalex.org/W2963758027","https://openalex.org/W2963880187","https://openalex.org/W2963902384","https://openalex.org/W2963980128","https://openalex.org/W2964080601","https://openalex.org/W2964118342","https://openalex.org/W2964225075","https://openalex.org/W2964896648","https://openalex.org/W2976658881","https://openalex.org/W2984121207","https://openalex.org/W2990069284","https://openalex.org/W3035372819","https://openalex.org/W3095753865","https://openalex.org/W3103211586","https://openalex.org/W3109813419","https://openalex.org/W3186953717","https://openalex.org/W3199267905"],"related_works":["https://openalex.org/W4388893791","https://openalex.org/W4290852288","https://openalex.org/W4283207562","https://openalex.org/W4210416330","https://openalex.org/W3217195652","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W2330246314"],"abstract_inverted_index":{"We":[0,89,165],"introduce":[1],"dense":[2],"relational":[3,19,59,63,163],"captioning,":[4,199],"a":[5,24,51,75,87],"novel":[6],"image":[7,53,198],"captioning":[8,28],"task":[9],"which":[10,119,129],"aims":[11],"to":[12,18,50,79,93,97,102,196],"generate":[13,98,172],"multiple":[14],"captions":[15,99,137],"with":[16,160],"respect":[17],"information":[20,78],"between":[21,35,65],"objects":[22],"in":[23,42,86],"visual":[25],"scene.":[26],"Relational":[27],"provides":[29],"explicit":[30,162],"descriptions":[31],"for":[32,126,140],"each":[33,107,127,141],"relationship":[34],"object":[36,158],"combinations.":[37],"This":[38],"framework":[39,92,195],"is":[40,130],"advantageous":[41],"both":[43],"diversity":[44],"and":[45,138,175,186,203],"amount":[46],"of":[47,84,106,121,150,193],"information,":[48],"leading":[49],"comprehensive":[52],"understanding":[54,64],"based":[55],"on":[56,182],"relationships,":[57],"e.g.,":[58],"proposal":[60],"generation.":[61],"For":[62],"objects,":[66],"the":[67,81,104,114,135,148,157],"part-of-speech":[68],"(POS;":[69],"i.e.,":[70],"subject-object-predicate":[71],"categories)":[72],"can":[73,152,171],"be":[74,153],"valuable":[76],"prior":[77],"guide":[80],"causal":[82],"sequence":[83],"words":[85],"caption.":[88],"enforce":[90],"our":[91,168,194],"learn":[94],"not":[95],"only":[96],"but":[100],"also":[101],"understand":[103],"POS":[105,128,139],"word.":[108,142],"To":[109],"this":[110],"end,":[111],"we":[112,145,190],"propose":[113],"multi-task":[115],"triple-stream":[116],"network":[117],"(MTTSNet)":[118],"consists":[120],"three":[122],"recurrent":[123],"units":[124],"responsible":[125],"trained":[131],"by":[132,155],"jointly":[133],"predicting":[134],"correct":[136],"In":[143],"addition,":[144],"found":[146],"that":[147,167],"performance":[149],"MTTSNet":[151],"improved":[154],"modulating":[156],"embeddings":[159],"an":[161],"module.":[164],"demonstrate":[166],"proposed":[169],"model":[170],"more":[173],"diverse":[174],"richer":[176],"captions,":[177],"via":[178],"extensive":[179],"experimental":[180],"analysis":[181],"large":[183],"scale":[184],"datasets":[185],"several":[187],"metrics.":[188],"Then,":[189],"present":[191],"applications":[192],"holistic":[197],"scene":[200],"graph":[201],"generation,":[202],"retrieval":[204],"tasks.":[205]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3205625102","counts_by_year":[{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3}],"updated_date":"2025-01-17T13:51:44.810647","created_date":"2021-10-25"}