{"id":"https://openalex.org/W4416744808","doi":"https://doi.org/10.1007/s40747-025-02183-2","title":"Enhancing image captioning with spatial relational attention and grid decoder","display_name":"Enhancing image captioning with spatial relational attention and grid decoder","publication_year":2025,"publication_date":"2025-11-27","ids":{"openalex":"https://openalex.org/W4416744808","doi":"https://doi.org/10.1007/s40747-025-02183-2"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-025-02183-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-02183-2","pdf_url":null,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex &amp; Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1007/s40747-025-02183-2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101308301","display_name":"Xin Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I179324530","display_name":"Jilin University of Finance and Economics","ror":"https://ror.org/04az9eh24","country_code":"CN","type":"education","lineage":["https://openalex.org/I179324530"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Deng","raw_affiliation_strings":["Jilin University of Finance and Economics, Changchun, 130000, Jilin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jilin University of Finance and Economics, Changchun, 130000, Jilin, China","institution_ids":["https://openalex.org/I179324530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109753319","display_name":"Yihuan Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I106645853","display_name":"Changchun University of Science and Technology","ror":"https://ror.org/007mntk44","country_code":"CN","type":"education","lineage":["https://openalex.org/I106645853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihuan Zhu","raw_affiliation_strings":["Changchun University of Science and Technology, Changchun, 130000, Jilin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Changchun University of Science and Technology, Changchun, 130000, Jilin, China","institution_ids":["https://openalex.org/I106645853"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102179070","display_name":"Honghua Xu","orcid":"https://orcid.org/0009-0009-7071-5929"},"institutions":[{"id":"https://openalex.org/I106645853","display_name":"Changchun University of Science and Technology","ror":"https://ror.org/007mntk44","country_code":"CN","type":"education","lineage":["https://openalex.org/I106645853"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Honghua Xu","raw_affiliation_strings":["Changchun University of Science and Technology, Changchun, 130000, Jilin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Changchun University of Science and Technology, Changchun, 130000, Jilin, China","institution_ids":["https://openalex.org/I106645853"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102179070"],"corresponding_institution_ids":["https://openalex.org/I106645853"],"apc_list":{"value":2190,"currency":"USD","value_usd":2190},"apc_paid":{"value":2190,"currency":"USD","value_usd":2190},"fwci":0.5458,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70375869,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"12","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.963699996471405,"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":0.963699996471405,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0066999997943639755,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.004600000102072954,"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":0.7861999869346619},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7696999907493591},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.7200000286102295},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6514000296592712},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5874999761581421},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5473999977111816},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.534500002861023},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4779999852180481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.789900004863739},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7861999869346619},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7696999907493591},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.7200000286102295},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6514000296592712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5949000120162964},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5874999761581421},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5473999977111816},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.534500002861023},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4779999852180481},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4465999901294708},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.4072999954223633},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.38499999046325684},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2540000081062317},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-025-02183-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-02183-2","pdf_url":null,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex &amp; Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:cefcc7f3e8b14997b113f4d8ba63b7bb","is_oa":true,"landing_page_url":"https://doaj.org/article/cefcc7f3e8b14997b113f4d8ba63b7bb","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complex & Intelligent Systems, Vol 12, Iss 1, Pp 1-13 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-025-02183-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-02183-2","pdf_url":null,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex &amp; Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2506483933","https://openalex.org/W2745461083","https://openalex.org/W2890531016","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2986670728","https://openalex.org/W3034655362","https://openalex.org/W3034689697","https://openalex.org/W3035284526","https://openalex.org/W3175824375","https://openalex.org/W3203701986","https://openalex.org/W4213019189","https://openalex.org/W4404479988"],"related_works":[],"abstract_inverted_index":{"This":[0,82],"paper":[1],"presents":[2],"a":[3,10,64],"novel":[4],"image":[5,102,113],"description":[6],"model":[7,40,56,110,126],"that":[8,107],"integrates":[9],"spatial":[11,43,50,123],"relational":[12],"attention":[13],"mechanism":[14],"to":[15,20,47,67,140],"enhance":[16],"the":[17,39,53,59,76,85,93,108],"model's":[18],"ability":[19],"understand":[21],"and":[22,34,87,100,131,137],"generate":[23],"accurate":[24,99],"descriptions":[25],"of":[26,78,89],"images.":[27],"By":[28],"combining":[29],"absolute":[30],"position":[31,36],"encoding":[32,37],"(APE)":[33],"relative":[35],"(RPE),":[38],"improves":[41],"its":[42],"awareness,":[44],"enabling":[45],"it":[46],"capture":[48],"intricate":[49,122],"relationships":[51],"within":[52],"image.":[54],"The":[55,125],"also":[57],"introduces":[58],"grid":[60],"decoder,":[61],"which":[62],"utilizes":[63],"multi-path":[65],"structure":[66],"effectively":[68],"fuse":[69],"information":[70],"from":[71],"multiple":[72],"encoder":[73],"layers,":[74],"overcoming":[75],"limitations":[77],"traditional":[79,141],"single-path":[80],"decoders.":[81],"design":[83],"promotes":[84],"interaction":[86],"integration":[88],"multi-level":[90],"features,":[91],"improving":[92],"model\u2019s":[94],"performance":[95],"in":[96,117],"generating":[97],"more":[98,128],"natural":[101],"de-scriptions.":[103],"Experimental":[104],"results":[105],"demonstrated":[106],"proposed":[109],"outperforms":[111],"existing":[112],"captioning":[114],"models,":[115],"particularly":[116],"processing":[118],"complex":[119],"images":[120],"with":[121],"layouts.":[124],"generated":[127],"contextually":[129],"relevant":[130],"coherent":[132],"de-scriptions,":[133],"showing":[134],"higher":[135],"accuracy":[136],"naturalness":[138],"compared":[139],"methods.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-11-28T00:00:00"}
