{"id":"https://openalex.org/W3112857531","doi":"https://doi.org/10.1109/access.2020.3024639","title":"A Sparse Transformer-Based Approach for Image Captioning","display_name":"A Sparse Transformer-Based Approach for Image Captioning","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3112857531","doi":"https://doi.org/10.1109/access.2020.3024639","mag":"3112857531"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.3024639","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3024639","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09199872.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09199872.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058737960","display_name":"Lei Zhou","orcid":"https://orcid.org/0000-0003-0860-0724"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhou Lei","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101689363","display_name":"Congcong Zhou","orcid":"https://orcid.org/0000-0002-7215-3765"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Congcong Zhou","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062618254","display_name":"Shengbo Chen","orcid":"https://orcid.org/0000-0002-9026-8128"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengbo Chen","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088202431","display_name":"Yiyong Huang","orcid":"https://orcid.org/0000-0002-5977-4786"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiyong Huang","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072602296","display_name":"Xianrui Liu","orcid":"https://orcid.org/0000-0002-5068-512X"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianrui Liu","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5058737960"],"corresponding_institution_ids":["https://openalex.org/I141962983"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.3925,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.6340758,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"8","issue":null,"first_page":"213437","last_page":"213446"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9954000115394592,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9945999979972839,"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":0.9531105756759644},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8711569309234619},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6034188866615295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6007932424545288},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5520899891853333},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.48718613386154175},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4581088721752167},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4497048556804657},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44237253069877625},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3934519290924072},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3713645935058594}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9531105756759644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8711569309234619},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6034188866615295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6007932424545288},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5520899891853333},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.48718613386154175},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4581088721752167},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4497048556804657},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44237253069877625},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3934519290924072},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3713645935058594},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.3024639","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3024639","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09199872.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:8d37acadce0441f6b826f861c201713c","is_oa":true,"landing_page_url":"https://doaj.org/article/8d37acadce0441f6b826f861c201713c","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 213437-213446 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.3024639","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3024639","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09199872.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"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/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1706851893","display_name":null,"funder_award_id":"19511121002","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"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/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/G4580770338","display_name":null,"funder_award_id":"2017YFB0701600","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G466649759","display_name":null,"funder_award_id":"2017Y","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5707527883","display_name":null,"funder_award_id":"61572306","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/G7520884868","display_name":null,"funder_award_id":"2017YFB0701600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G820651143","display_name":null,"funder_award_id":"B07016","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8340078520","display_name":null,"funder_award_id":"2017YF","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8823009050","display_name":null,"funder_award_id":"2017YFB","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3112857531.pdf","grobid_xml":"https://content.openalex.org/works/W3112857531.grobid-xml"},"referenced_works_count":80,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W648786980","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1773149199","https://openalex.org/W1811254738","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1895989618","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2133459682","https://openalex.org/W2154652894","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2519887557","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2575842049","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2754927243","https://openalex.org/W2795151422","https://openalex.org/W2808206191","https://openalex.org/W2885013662","https://openalex.org/W2887585070","https://openalex.org/W2890531016","https://openalex.org/W2896348597","https://openalex.org/W2901988662","https://openalex.org/W2940744433","https://openalex.org/W2955227499","https://openalex.org/W2962706528","https://openalex.org/W2962760898","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963403868","https://openalex.org/W2964015378","https://openalex.org/W2964121744","https://openalex.org/W2965359408","https://openalex.org/W2965697393","https://openalex.org/W2970569830","https://openalex.org/W2971310675","https://openalex.org/W2972897806","https://openalex.org/W2973642807","https://openalex.org/W2979747405","https://openalex.org/W2982553922","https://openalex.org/W2984138079","https://openalex.org/W2986670728","https://openalex.org/W2990818246","https://openalex.org/W2997753998","https://openalex.org/W3034655362","https://openalex.org/W3034984754","https://openalex.org/W3035284526","https://openalex.org/W3105136412","https://openalex.org/W4288289156","https://openalex.org/W4288329833","https://openalex.org/W4323654151","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6621543089","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6638742206","https://openalex.org/W6639102338","https://openalex.org/W6682631176","https://openalex.org/W6726873649","https://openalex.org/W6729624334","https://openalex.org/W6739901393","https://openalex.org/W6744684495","https://openalex.org/W6761628794","https://openalex.org/W6763643401","https://openalex.org/W6765264507","https://openalex.org/W6767200354","https://openalex.org/W6772230799","https://openalex.org/W6775772702","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","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":{"Image":[0],"Captioning":[1],"is":[2,44,81,87,199],"the":[3,57,60,63,67,112,137,143,149,157,163,167,178],"task":[4],"of":[5,19,99,130,139,156],"providing":[6],"a":[7,76,96,128],"natural":[8,26],"language":[9,27],"description":[10],"for":[11,83],"an":[12],"image.":[13],"It":[14,160],"has":[15],"caught":[16],"significant":[17],"amounts":[18],"attention":[20,158],"from":[21],"both":[22],"computer":[23],"vision":[24],"and":[25,108,172,188,194],"processing":[28],"communities.":[29],"Most":[30],"image":[31,53,71,84,100,115,170],"captioning":[32,85],"models":[33],"adopt":[34],"deep":[35,78],"encoder-decoder":[36,79],"architectures":[37],"to":[38,46,69,105],"achieve":[39],"state-of-the-art":[40],"performances.":[41],"However,":[42],"it":[43],"difficult":[45],"model":[47,80,164,184],"knowledge":[48],"on":[49,89,103,142,166,192],"relationships":[50],"between":[51,114],"input":[52],"region":[54,116],"pairs":[55,117],"in":[56,62,177],"encoder.":[58],"Furthermore,":[59],"word":[61],"decoder":[64,135],"hardly":[65],"knows":[66],"correlation":[68],"specific":[70],"regions.":[72],"In":[73],"this":[74],"article,":[75],"novel":[77],"proposed":[82],"which":[86],"developed":[88],"sparse":[90],"Transformer":[91],"framework.":[92],"The":[93,134],"encoder":[94],"adopts":[95],"multi-level":[97],"representation":[98],"features":[101],"based":[102],"self-attention":[104,122,141],"exploit":[106],"low-level":[107],"high-level":[109],"features,":[110],"naturally":[111],"correlations":[113],"are":[118],"adequately":[119],"modeled":[120],"as":[121,127],"operation":[123],"can":[124,161],"be":[125],"seen":[126],"way":[129],"encoding":[131],"pairwise":[132],"relationships.":[133],"improves":[136],"concentration":[138],"multi-head":[140],"global":[144],"context":[145],"by":[146],"explicitly":[147],"selecting":[148],"most":[150],"relevant":[151],"segments":[152],"at":[153,201],"each":[154],"row":[155],"matrix.":[159],"help":[162],"focus":[165],"more":[168,174],"contributing":[169],"regions":[171],"generate":[173],"accurate":[175],"words":[176],"context.":[179],"Experiments":[180],"demonstrate":[181],"that":[182],"our":[183],"outperforms":[185],"previous":[186],"methods":[187],"achieves":[189],"higher":[190],"performance":[191],"MSCOCO":[193],"Flickr30k":[195],"datasets.":[196],"Our":[197],"code":[198],"available":[200],"https://github.com/2014gaokao/ImageCaptioning.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}