{"id":"https://openalex.org/W4392151980","doi":"https://doi.org/10.1109/tmm.2024.3369863","title":"DCMSTRD: End-to-end Dense Captioning via Multi-Scale Transformer Decoding","display_name":"DCMSTRD: End-to-end Dense Captioning via Multi-Scale Transformer Decoding","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4392151980","doi":"https://doi.org/10.1109/tmm.2024.3369863"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3369863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3369863","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/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Zhuang Shao","raw_affiliation_strings":["School of Engineering, Newcastle University, Newcastle upon Tyne, U.K"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Newcastle University, Newcastle upon Tyne, U.K","institution_ids":["https://openalex.org/I84884186"]}]},{"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, Sheffield, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, 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"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Pang","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China","Shanghai Artificial Intelligence Laboratory, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077948412"],"corresponding_institution_ids":["https://openalex.org/I84884186"],"apc_list":null,"apc_paid":null,"fwci":8.3896,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.98414074,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"7581","last_page":"7593"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.998199999332428,"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":0.9977999925613403,"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/computer-science","display_name":"Computer science","score":0.815346896648407},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.8074073791503906},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6855250597000122},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.668398916721344},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5703455805778503},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2304036021232605},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.22457385063171387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2034229040145874},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.18024417757987976},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06681793928146362}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.815346896648407},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8074073791503906},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6855250597000122},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.668398916721344},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5703455805778503},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2304036021232605},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.22457385063171387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2034229040145874},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.18024417757987976},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06681793928146362},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2024.3369863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3369863","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:209263","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":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1584238570","https://openalex.org/W1905882502","https://openalex.org/W2064675550","https://openalex.org/W2102605133","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2302086703","https://openalex.org/W2322020277","https://openalex.org/W2552002300","https://openalex.org/W2745461083","https://openalex.org/W2776346076","https://openalex.org/W2886641317","https://openalex.org/W2903617461","https://openalex.org/W2950635152","https://openalex.org/W2962766617","https://openalex.org/W2963351113","https://openalex.org/W2963758027","https://openalex.org/W2973233205","https://openalex.org/W2974212192","https://openalex.org/W2979987972","https://openalex.org/W2981413347","https://openalex.org/W2986670728","https://openalex.org/W3005971801","https://openalex.org/W3019723613","https://openalex.org/W3023511145","https://openalex.org/W3023584964","https://openalex.org/W3096609285","https://openalex.org/W3097062010","https://openalex.org/W3107015116","https://openalex.org/W3138516171","https://openalex.org/W3167939936","https://openalex.org/W3174377922","https://openalex.org/W3176524055","https://openalex.org/W3211865849","https://openalex.org/W4214663214","https://openalex.org/W4220899212","https://openalex.org/W4225512839","https://openalex.org/W4226083961","https://openalex.org/W4226094317","https://openalex.org/W4226280874","https://openalex.org/W4297450596","https://openalex.org/W4308785766","https://openalex.org/W4312361860","https://openalex.org/W4312554764","https://openalex.org/W4318953563","https://openalex.org/W4327522797","https://openalex.org/W4385245566","https://openalex.org/W4386137987","https://openalex.org/W4387449204","https://openalex.org/W4387522812","https://openalex.org/W4387643249","https://openalex.org/W4387968078","https://openalex.org/W6685230081","https://openalex.org/W6763509872","https://openalex.org/W6780226713","https://openalex.org/W6784094891","https://openalex.org/W6790690058"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4210416330","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],"captioning":[1,93,103],"creates":[2],"diverse":[3],"Region":[4],"of":[5,51,60,70,116,146],"Interests":[6],"(RoIs)":[7],"descriptions":[8],"for":[9,33],"complex":[10],"visual":[11],"scenes.":[12],"While":[13],"promising":[14],"results":[15],"have":[16],"been":[17],"obtained,":[18],"several":[19],"issues":[20],"persist.":[21],"In":[22],"particular:":[23],"1)":[24],"it":[25],"is":[26],"hard":[27],"to":[28,46,75],"find":[29],"the":[30,48,58,68,84,113,117,149,157],"optimal":[31],"parameters":[32],"artificially":[34,85],"designed":[35,86],"modules":[36,87],"(e.g.,":[37],"non-maximum":[38],"suppression":[39],"(NMS))":[40],"causing":[41],"redundancies":[42],"and":[43,54,88,107],"fewer":[44],"interactions":[45],"benefit":[47],"two":[49],"sub-tasks":[50],"RoI":[52,55],"detection":[53],"captioning;":[56],"2)":[57],"absence":[59],"a":[61,125,141],"multi-scale":[62,96,118,126,129],"decoder":[63,131],"in":[64],"current":[65,158],"methods":[66],"hinders":[67],"acquisition":[69],"scale-invariant":[71],"features,":[72],"thus":[73],"leading":[74],"poor":[76],"performance.":[77],"To":[78,110],"tackle":[79],"these":[80],"limitations,":[81],"we":[82,123],"bypass":[83],"present":[89],"an":[90],"end-to-end":[91],"dense":[92,102],"framework":[94],"via":[95],"transformer":[97],"decoding":[98],"(DCMSTRD).":[99],"DCMSTRD":[100],"solves":[101],"by":[104],"set":[105],"matching":[106],"prediction":[108],"instead.":[109],"further":[111],"enhance":[112],"discriminative":[114],"quality":[115],"representations":[119],"during":[120],"caption":[121],"generation,":[122],"introduce":[124],"module,":[127],"termed":[128],"language":[130],"(MSLD).":[132],"Our":[133],"proposed":[134],"method":[135],"tested":[136],"on":[137,148],"standard":[138],"datasets":[139],"achieves":[140],"mean":[142],"Average":[143],"Precision":[144],"(mAP)":[145],"16.7%":[147],"challenging":[150],"VG-COCO":[151],"dataset,":[152],"demonstrating":[153],"its":[154],"effectiveness":[155],"against":[156],"methods.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}