{"id":"https://openalex.org/W4318953563","doi":"https://doi.org/10.1109/tmm.2023.3241517","title":"Textual Context-Aware Dense Captioning With Diverse Words","display_name":"Textual Context-Aware Dense Captioning With Diverse Words","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4318953563","doi":"https://doi.org/10.1109/tmm.2023.3241517"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3241517","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3241517","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","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/A5077948412","display_name":"Zhuang Shao","orcid":"https://orcid.org/0000-0001-7824-0985"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Zhuang Shao","raw_affiliation_strings":["Warwick Manufacturing Group, University of Warwick, U.K"],"affiliations":[{"raw_affiliation_string":"Warwick Manufacturing Group, University of Warwick, U.K","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046605531","display_name":"Jungong Han","orcid":"https://orcid.org/0000-0003-4361-956X"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jungong Han","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, U.K","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087052285","display_name":"Kurt Debattista","orcid":"https://orcid.org/0000-0003-2982-5199"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kurt Debattista","raw_affiliation_strings":["Warwick Manufacturing Group, University of Warwick, U.K"],"affiliations":[{"raw_affiliation_string":"Warwick Manufacturing Group, University of Warwick, U.K","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086887025","display_name":"Yanwei Pang","orcid":"https://orcid.org/0000-0001-6670-3727"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Pang","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077948412"],"corresponding_institution_ids":["https://openalex.org/I39555362"],"apc_list":null,"apc_paid":null,"fwci":7.5524,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.98163425,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"25","issue":null,"first_page":"8753","last_page":"8766"},"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":0.9972000122070312,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9939000010490417,"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":0.9768087863922119},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8840539455413818},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6836870312690735},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6501209139823914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5620283484458923},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5306369662284851},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44842132925987244},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3988284766674042},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1376895010471344},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13523060083389282}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9768087863922119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8840539455413818},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6836870312690735},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6501209139823914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5620283484458923},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5306369662284851},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44842132925987244},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3988284766674042},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1376895010471344},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13523060083389282},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2023.3241517","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3241517","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:195981","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8700000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2102605133","https://openalex.org/W2104636679","https://openalex.org/W2117539524","https://openalex.org/W2133512280","https://openalex.org/W2144506857","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2302086703","https://openalex.org/W2322020277","https://openalex.org/W2523246573","https://openalex.org/W2552002300","https://openalex.org/W2776346076","https://openalex.org/W2886641317","https://openalex.org/W2890531016","https://openalex.org/W2903617461","https://openalex.org/W2913618459","https://openalex.org/W2963351113","https://openalex.org/W2963758027","https://openalex.org/W2973233205","https://openalex.org/W2974212192","https://openalex.org/W2979987972","https://openalex.org/W2984009799","https://openalex.org/W3023584964","https://openalex.org/W3097062010","https://openalex.org/W3107015116","https://openalex.org/W3111980808","https://openalex.org/W3167939936","https://openalex.org/W3174377922","https://openalex.org/W3208871062","https://openalex.org/W4214663214","https://openalex.org/W4220899212","https://openalex.org/W4225512839","https://openalex.org/W4226083961","https://openalex.org/W4297450596","https://openalex.org/W4312554764","https://openalex.org/W6630875275","https://openalex.org/W6685230081","https://openalex.org/W6727249380","https://openalex.org/W6739901393","https://openalex.org/W6765997584","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661"],"abstract_inverted_index":{"Dense":[0,81],"captioning":[1,35,76,164],"generates":[2],"more":[3],"detailed":[4],"spoken":[5],"descriptions":[6],"for":[7],"complex":[8],"visual":[9,31],"scenes.":[10],"Despite":[11],"several":[12],"promising":[13],"leads,":[14],"existing":[15],"methods":[16,170],"still":[17],"have":[18],"two":[19],"broad":[20],"limitations:":[21],"1)":[22],"The":[23,155],"vast":[24],"majority":[25],"of":[26,50,115,130,134,173],"prior":[27],"arts":[28],"only":[29],"consider":[30],"contextual":[32],"clues":[33],"during":[34,97,147],"but":[36],"ignore":[37],"potentially":[38],"important":[39],"textual":[40,86,123],"context;":[41],"2)":[42],"current":[43],"imbalanced":[44],"learning":[45],"mechanisms":[46],"limit":[47],"the":[48,54,94,103,116,121,131,161,168],"diversity":[49],"vocabulary":[51,95],"learned":[52],"from":[53,88],"dictionary,":[55],"thus":[56],"giving":[57],"rise":[58],"to":[59,119,149],"low":[60],"language-learning":[61],"efficiency.":[62],"To":[63],"alleviate":[64],"these":[65],"gaps,":[66],"in":[67,171],"this":[68],"paper,":[69],"we":[70,100,126],"propose":[71,102,138],"an":[72],"end-to-end":[73],"enhanced":[74],"dense":[75,163],"architecture,":[77],"namely":[78],"Enhanced":[79],"Transformer":[80,117],"Captioner":[82],"(ETDC),":[83],"which":[84,108],"obtains":[85],"context":[87,136],"surrounding":[89,122],"regions":[90],"and":[91,137,166],"dynamically":[92],"diversifies":[93],"bank":[96],"captioning.":[98],"Concretely,":[99],"first":[101],"Textual":[104],"Context":[105],"Module":[106],"(TCM),":[107],"is":[109,158],"integrated":[110],"into":[111],"each":[112],"self-attention":[113],"layer":[114],"decoder,":[118],"capture":[120],"context.":[124],"Moreover,":[125],"take":[127],"full":[128],"advantage":[129],"class":[132],"information":[133],"object":[135],"a":[139],"Dynamic":[140],"Vocabulary":[141],"Frequency":[142],"Histogram":[143],"(DVFH)":[144],"re-sampling":[145],"strategy":[146],"training":[148],"balance":[150],"words":[151],"with":[152],"different":[153],"frequencies.":[154],"proposed":[156],"method":[157],"tested":[159],"on":[160],"standard":[162],"datasets":[165],"surpasses":[167],"state-of-the-art":[169],"terms":[172],"mean":[174],"Average":[175],"Precision":[176],"(mAP).":[177]},"counts_by_year":[{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":35},{"year":2023,"cited_by_count":14}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}