{"id":"https://openalex.org/W4312941295","doi":"https://doi.org/10.1109/tmm.2022.3215861","title":"TSFNet: Triple-Steam Image Captioning","display_name":"TSFNet: Triple-Steam Image Captioning","publication_year":2022,"publication_date":"2022-11-03","ids":{"openalex":"https://openalex.org/W4312941295","doi":"https://doi.org/10.1109/tmm.2022.3215861"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3215861","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3215861","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/A5014620591","display_name":"Nannan Hu","orcid":"https://orcid.org/0000-0002-4080-7891"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nannan Hu","raw_affiliation_strings":["Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089582342","display_name":"Yue Ming","orcid":"https://orcid.org/0000-0001-7105-4207"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Ming","raw_affiliation_strings":["Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7105-4207","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100780601","display_name":"Chunxiao Fan","orcid":"https://orcid.org/0000-0002-3607-4904"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunxiao Fan","raw_affiliation_strings":["Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101581669","display_name":"Fan Feng","orcid":"https://orcid.org/0000-0001-7959-2472"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Feng","raw_affiliation_strings":["Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7959-2472","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060843754","display_name":"Boyang Lyu","orcid":"https://orcid.org/0000-0002-5396-7464"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyang Lyu","raw_affiliation_strings":["Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.9788,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.76670911,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"25","issue":null,"first_page":"6904","last_page":"6916"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9962000250816345,"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":0.9811999797821045,"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/closed-captioning","display_name":"Closed captioning","score":0.9278836250305176},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8488919734954834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5775867700576782},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5019757747650146},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.49235808849334717},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.47907811403274536},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44698193669319153},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4378505051136017},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.42275339365005493},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3890075981616974},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33315378427505493},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3060350716114044},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.18426552414894104}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9278836250305176},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8488919734954834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5775867700576782},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5019757747650146},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49235808849334717},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.47907811403274536},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44698193669319153},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4378505051136017},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.42275339365005493},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3890075981616974},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33315378427505493},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3060350716114044},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.18426552414894104},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2022.3215861","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3215861","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.46000000834465027,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5457963859","display_name":null,"funder_award_id":"62076030","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W877909479","https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2108325777","https://openalex.org/W2149557440","https://openalex.org/W2302086703","https://openalex.org/W2463955103","https://openalex.org/W2506483933","https://openalex.org/W2552161745","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2755125693","https://openalex.org/W2890531016","https://openalex.org/W2904551248","https://openalex.org/W2913618459","https://openalex.org/W2962982762","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963536419","https://openalex.org/W2965597639","https://openalex.org/W2966683369","https://openalex.org/W2981165461","https://openalex.org/W2981994675","https://openalex.org/W2983141445","https://openalex.org/W2986670728","https://openalex.org/W2988916019","https://openalex.org/W2990069284","https://openalex.org/W2990216675","https://openalex.org/W3034689697","https://openalex.org/W3034733309","https://openalex.org/W3035284526","https://openalex.org/W3045147787","https://openalex.org/W3080813890","https://openalex.org/W3092767330","https://openalex.org/W3103651098","https://openalex.org/W3106925514","https://openalex.org/W3110014757","https://openalex.org/W3135254306","https://openalex.org/W3167939936","https://openalex.org/W3173961205","https://openalex.org/W3174042809","https://openalex.org/W3174377922","https://openalex.org/W3174930619","https://openalex.org/W3195680250","https://openalex.org/W3205625102","https://openalex.org/W3211865849","https://openalex.org/W3214200059","https://openalex.org/W4214617019","https://openalex.org/W4304080274","https://openalex.org/W6621906925","https://openalex.org/W6631190155","https://openalex.org/W6638549007","https://openalex.org/W6676497082","https://openalex.org/W6678262379","https://openalex.org/W6715144786","https://openalex.org/W6739901393"],"related_works":["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","https://openalex.org/W2330246314","https://openalex.org/W2293263892"],"abstract_inverted_index":{"Image":[0],"captioning":[1,226],"is":[2,24,124],"a":[3,8,25,90,118,149,160],"challenging":[4],"task":[5],"that":[6,218],"generates":[7,233],"natural":[9],"language":[10],"description":[11],"based":[12],"on":[13,41,202],"the":[14,18,31,42,53,64,74,98,102,154,166,173,185,191,203,210,219],"visual":[15,60,70,109,129,180],"understanding":[16],"of":[17,34,55,76,101,136,143,169,193],"given":[19],"image.":[20],"Significant":[21],"region":[22],"representation":[23,151,168,176],"milestone":[26],"in":[27,111,115,228],"image":[28,112,225],"captioning.":[29,113],"Despite":[30],"great":[32],"success":[33],"existing":[35],"region-based":[36],"works,":[37],"they":[38],"only":[39],"focus":[40],"salient":[43],"objects":[44,48],"and":[45,59,68,80,105,132,172,213,232,236],"encode":[46],"these":[47],"independently,":[49],"still":[50],"plagued":[51],"by":[52],"lack":[54],"global":[56,65,179],"contextual":[57,66],"information":[58,67],"relationships.":[61],"In":[62,85],"fact,":[63],"structured":[69],"relationships":[71],"are":[72,146],"exactly":[73],"merits":[75],"traditional":[77],"grid":[78],"features":[79,142,171],"emerging":[81],"scene":[82,106],"graph":[83,107],"features.":[84,138],"this":[86],"paper,":[87],"we":[88,158,198],"present":[89],"Triple-Steam":[91],"Feature":[92],"Fusion":[93],"Network":[94],"(TSFNet)":[95],"to":[96,126,152,177,208],"leverage":[97],"complementary":[99],"advantages":[100],"grid,":[103],"region,":[104],"triple-steam":[108,170],"representations":[110],"Concretely,":[114],"our":[116,194],"TSFNet,":[117],"novel":[119],"Dual-level":[120],"Attention":[121],"(DA)":[122],"mechanism":[123],"proposed":[125,220],"simultaneously":[127],"explore":[128],"intrinsic":[130],"properties":[131],"word-related":[133],"attributes":[134],"uniformly":[135],"different":[137,144],"Then":[139],"attention":[140,175],"enhanced":[141],"modalities":[145],"mapped":[147],"into":[148],"joint":[150,174],"guide":[153],"caption":[155],"generation.":[156],"Moreover,":[157],"design":[159],"new":[161],"global-aware":[162],"decoder,":[163],"which":[164],"leverages":[165],"concatenated":[167],"obtain":[178],"guidance":[181],"information,":[182],"further":[183],"refine":[184],"complex":[186],"multimodal":[187],"reasoning.":[188],"To":[189],"verify":[190],"effectiveness":[192],"feature":[195],"fusion":[196],"model,":[197],"perform":[199],"extensive":[200],"experiments":[201],"highly":[204],"competitive":[205],"MSCOCO":[206],"dataset":[207],"evaluate":[209],"model":[211],"quantitatively":[212],"qualitatively.":[214],"The":[215],"results":[216],"illustrate":[217],"framework":[221],"outperforms":[222],"many":[223],"state-of-the-art":[224],"approaches":[227],"various":[229],"evaluation":[230],"metrics,":[231],"more":[234],"accurate":[235],"abundant":[237],"captions.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}