{"id":"https://openalex.org/W4391717242","doi":"https://doi.org/10.1007/s40747-023-01341-8","title":"Exploring better image captioning with grid features","display_name":"Exploring better image captioning with grid features","publication_year":2024,"publication_date":"2024-02-10","ids":{"openalex":"https://openalex.org/W4391717242","doi":"https://doi.org/10.1007/s40747-023-01341-8"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-023-01341-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-023-01341-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-023-01341-8.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s40747-023-01341-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101437836","display_name":"Jie Yan","orcid":"https://orcid.org/0000-0001-9512-322X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jie Yan","raw_affiliation_strings":["College of Systems Engineering, National University of Defense Technology, Changsha, 410073, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha, 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100602725","display_name":"Yuxiang Xie","orcid":"https://orcid.org/0000-0002-8784-1923"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiang Xie","raw_affiliation_strings":["College of Systems Engineering, National University of Defense Technology, Changsha, 410073, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha, 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079425523","display_name":"Yanming Guo","orcid":"https://orcid.org/0000-0001-9184-5313"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanming Guo","raw_affiliation_strings":["College of Systems Engineering, National University of Defense Technology, Changsha, 410073, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha, 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082811985","display_name":"Yingmei Wei","orcid":"https://orcid.org/0000-0003-4568-551X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingmei Wei","raw_affiliation_strings":["College of Systems Engineering, National University of Defense Technology, Changsha, 410073, China"],"raw_orcid":"https://orcid.org/0000-0003-4568-551X","affiliations":[{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha, 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041956475","display_name":"Xidao Luan","orcid":"https://orcid.org/0000-0002-5476-1767"},"institutions":[{"id":"https://openalex.org/I198357462","display_name":"Changsha University","ror":"https://ror.org/011d8sm39","country_code":"CN","type":"education","lineage":["https://openalex.org/I198357462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xidao Luan","raw_affiliation_strings":["College of Computer Engineering and Applied Mathematics, Changsha University, Changsha, 410073, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Engineering and Applied Mathematics, Changsha University, Changsha, 410073, China","institution_ids":["https://openalex.org/I198357462"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101437836"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":2.1427,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.87904053,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"10","issue":"3","first_page":"3541","last_page":"3556"},"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":0.9958000183105469,"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":0.9887999892234802,"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":0.9384167194366455},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7901647090911865},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.675800085067749},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.580086350440979},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5690225958824158},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5471224188804626},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4825703203678131},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46063148975372314},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4433193802833557},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41088879108428955},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37332814931869507},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3728543817996979},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3455880284309387},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.27234458923339844},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09104970097541809}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9384167194366455},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7901647090911865},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.675800085067749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.580086350440979},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5690225958824158},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5471224188804626},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4825703203678131},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46063148975372314},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4433193802833557},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41088879108428955},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37332814931869507},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3728543817996979},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3455880284309387},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27234458923339844},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09104970097541809},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-023-01341-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-023-01341-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-023-01341-8.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:301815a10ae24ec58c1221da31b9f2ab","is_oa":true,"landing_page_url":"https://doaj.org/article/301815a10ae24ec58c1221da31b9f2ab","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complex & Intelligent Systems, Vol 10, Iss 3, Pp 3541-3556 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-023-01341-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-023-01341-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-023-01341-8.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5616526104","display_name":null,"funder_award_id":"2021YFB3100800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6515052314","display_name":null,"funder_award_id":"2021YFB3100800","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7592982503","display_name":null,"funder_award_id":"2020AAA0108800","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7695114569","display_name":null,"funder_award_id":"2020AAA0108800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8062392985","display_name":null,"funder_award_id":"61806218","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4391717242.pdf"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W8316075","https://openalex.org/W956551720","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2197223256","https://openalex.org/W2302086703","https://openalex.org/W2463955103","https://openalex.org/W2506483933","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2885013662","https://openalex.org/W2886641317","https://openalex.org/W2890531016","https://openalex.org/W2896457183","https://openalex.org/W2901988662","https://openalex.org/W2938603906","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2964018924","https://openalex.org/W2976658881","https://openalex.org/W2985051484","https://openalex.org/W2986670728","https://openalex.org/W2989176720","https://openalex.org/W2990818246","https://openalex.org/W2997443031","https://openalex.org/W3034169961","https://openalex.org/W3034655362","https://openalex.org/W3035160838","https://openalex.org/W3035284526","https://openalex.org/W3035497460","https://openalex.org/W3044438666","https://openalex.org/W3044889983","https://openalex.org/W3098267758","https://openalex.org/W3161934848","https://openalex.org/W3167939936","https://openalex.org/W3171353004","https://openalex.org/W3173220247","https://openalex.org/W3173961205","https://openalex.org/W3174770825","https://openalex.org/W3196122027","https://openalex.org/W3198377975","https://openalex.org/W3203243482","https://openalex.org/W4210482049","https://openalex.org/W4320487288","https://openalex.org/W6605520847"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W2993670781","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661","https://openalex.org/W3009270862"],"abstract_inverted_index":{"Abstract":[0],"Nowadays,":[1],"Artificial":[2],"Intelligence":[3],"Generated":[4],"Content":[5],"(AIGC)":[6],"has":[7,30],"shown":[8],"promising":[9],"prospects":[10],"in":[11,92],"both":[12],"computer":[13],"vision":[14],"and":[15,53,155,176,184,193,209,241],"natural":[16],"language":[17],"processing":[18],"communities.":[19],"Meanwhile,":[20],"as":[21,136,160],"an":[22],"essential":[23],"aspect":[24],"of":[25,60,127,131,237],"AIGC,":[26],"image":[27,65,69,99,108,221],"to":[28,75,85,140,168,177,219,233],"captions":[29],"received":[31],"much":[32],"more":[33,51,248],"attention.":[34],"Recent":[35],"vision-language":[36],"research":[37,61],"is":[38],"developing":[39],"from":[40,145,173],"the":[41,88,93,122,137,156,181,188,194,206,229,235,238,242],"bulky":[42],"region":[43],"visual":[44,95,143,171,191,217],"representations":[45,96,192],"based":[46],"on":[47,64,87,228],"object":[48],"detectors":[49],"toward":[50],"convenient":[52],"flexible":[54],"grid":[55,94,147,153,174,190],"ones.":[56],"However,":[57],"this":[58,80,102],"kind":[59],"typically":[62],"concentrates":[63],"understanding":[66],"tasks":[67],"like":[68],"classification,":[70],"with":[71,113],"less":[72],"attention":[73],"paid":[74],"content":[76],"generation":[77],"tasks.":[78],"In":[79],"paper,":[81],"we":[82,104,162],"explore":[83],"how":[84],"capitalize":[86],"expressive":[89],"features":[90,154,196],"embedded":[91],"for":[97,202],"better":[98],"captioning.":[100],"To":[101],"end,":[103],"present":[105],"a":[106,128,164,199],"Transformer-based":[107],"captioning":[109,222,254],"model,":[110],"dubbed":[111],"FeiM,":[112],"two":[114,207],"straightforward":[115],"yet":[116],"effective":[117],"designs.":[118],"We":[119],"first":[120],"design":[121],"feature":[123,158,165],"queries":[124,159],"that":[125,245],"consist":[126],"limited":[129],"set":[130],"learnable":[132],"vectors,":[133],"which":[134],"act":[135],"local":[138,157,182],"signals":[139],"capture":[141],"specific":[142],"information":[144],"global":[146,152],"features.":[148],"Then,":[149],"taking":[150],"augmented":[151],"inputs,":[161],"develop":[163],"interaction":[166,179],"module":[167],"query":[169],"relevant":[170],"concepts":[172],"features,":[175],"enable":[178],"between":[180],"signal":[183],"overall":[185],"context.":[186],"Finally,":[187],"refined":[189],"linguistic":[195],"pass":[197],"through":[198],"Transformer":[200],"architecture":[201],"multi-modal":[203],"fusion.":[204],"With":[205],"novel":[208],"simple":[210],"designs,":[211],"FeiM":[212,246],"can":[213],"fully":[214],"leverage":[215],"meaningful":[216],"knowledge":[218],"improve":[220],"performance.":[223],"Extensive":[224],"experiments":[225],"are":[226],"performed":[227],"competitive":[230],"MSCOCO":[231],"benchmark":[232],"confirm":[234],"effectiveness":[236],"proposed":[239],"approach,":[240],"results":[243,250],"show":[244],"yields":[247],"eminent":[249],"than":[251],"existing":[252],"advanced":[253],"models.":[255]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}