{"id":"https://openalex.org/W4313890505","doi":"https://doi.org/10.3390/sym15010190","title":"Full-Memory Transformer for Image Captioning","display_name":"Full-Memory Transformer for Image Captioning","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4313890505","doi":"https://doi.org/10.3390/sym15010190"},"language":"en","primary_location":{"id":"doi:10.3390/sym15010190","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym15010190","pdf_url":"https://www.mdpi.com/2073-8994/15/1/190/pdf?version=1673256974","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-8994/15/1/190/pdf?version=1673256974","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028317852","display_name":"Tongwei Lu","orcid":"https://orcid.org/0000-0002-3900-6456"},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tongwei Lu","raw_affiliation_strings":["Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology, Wuhan 430205, China","School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan 430205, China"],"raw_orcid":"https://orcid.org/0000-0002-3900-6456","affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology, Wuhan 430205, China","institution_ids":["https://openalex.org/I91125648"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan 430205, China","institution_ids":["https://openalex.org/I91125648"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090403843","display_name":"Jiarong Wang","orcid":"https://orcid.org/0000-0002-3725-5248"},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiarong Wang","raw_affiliation_strings":["Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology, Wuhan 430205, China","School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan 430205, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology, Wuhan 430205, China","institution_ids":["https://openalex.org/I91125648"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan 430205, China","institution_ids":["https://openalex.org/I91125648"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013798584","display_name":"Feng Min","orcid":"https://orcid.org/0000-0002-6846-8916"},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fen Min","raw_affiliation_strings":["Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology, Wuhan 430205, China","School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan 430205, China"],"raw_orcid":"https://orcid.org/0000-0002-6846-8916","affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology, Wuhan 430205, China","institution_ids":["https://openalex.org/I91125648"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan 430205, China","institution_ids":["https://openalex.org/I91125648"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5028317852"],"corresponding_institution_ids":["https://openalex.org/I91125648"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":1.2521,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.81244053,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"15","issue":"1","first_page":"190","last_page":"190"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9955000281333923,"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":0.9927999973297119,"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":0.9154292345046997},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8063730001449585},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7942205667495728},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7012451887130737},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5394258499145508},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4869173765182495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48687806725502014},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.45781034231185913},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.4363497197628021},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41717109084129333},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41560328006744385},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3927941918373108},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3470410108566284},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2763921320438385}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9154292345046997},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8063730001449585},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7942205667495728},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7012451887130737},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5394258499145508},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4869173765182495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48687806725502014},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.45781034231185913},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4363497197628021},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41717109084129333},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41560328006744385},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3927941918373108},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3470410108566284},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2763921320438385},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/sym15010190","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym15010190","pdf_url":"https://www.mdpi.com/2073-8994/15/1/190/pdf?version=1673256974","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ee013be9068c439da3587dbec6fc7182","is_oa":false,"landing_page_url":"https://doaj.org/article/ee013be9068c439da3587dbec6fc7182","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry, Vol 15, Iss 1, p 190 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2073-8994/15/1/190/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/sym15010190","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry; Volume 15; Issue 1; Pages: 190","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/sym15010190","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym15010190","pdf_url":"https://www.mdpi.com/2073-8994/15/1/190/pdf?version=1673256974","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4313890505.pdf"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W8316075","https://openalex.org/W1514535095","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W1987835821","https://openalex.org/W2101105183","https://openalex.org/W2105103432","https://openalex.org/W2123301721","https://openalex.org/W2254252455","https://openalex.org/W2506483933","https://openalex.org/W2560313346","https://openalex.org/W2575842049","https://openalex.org/W2597985671","https://openalex.org/W2607579284","https://openalex.org/W2745461083","https://openalex.org/W2754927243","https://openalex.org/W2795151422","https://openalex.org/W2799009156","https://openalex.org/W2885013662","https://openalex.org/W2888321701","https://openalex.org/W2901988662","https://openalex.org/W2912924812","https://openalex.org/W2950626540","https://openalex.org/W2950813464","https://openalex.org/W2954182683","https://openalex.org/W2963101956","https://openalex.org/W2964110616","https://openalex.org/W2970569830","https://openalex.org/W3016697633","https://openalex.org/W3034984754","https://openalex.org/W3101313921","https://openalex.org/W3192478068","https://openalex.org/W3199014515","https://openalex.org/W4220992023","https://openalex.org/W6639102338","https://openalex.org/W6682631176","https://openalex.org/W6692647644","https://openalex.org/W6698228248","https://openalex.org/W6730549503","https://openalex.org/W6731356633","https://openalex.org/W6739901393","https://openalex.org/W6741121127","https://openalex.org/W6756667841","https://openalex.org/W6772381481","https://openalex.org/W6809322488"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"The":[0,66],"Transformer-based":[1],"approach":[2],"represents":[3],"the":[4,42,45,59,69,79,85,107,112,118,125,131,140,145,158,167],"state-of-the-art":[5],"in":[6,169],"image":[7,64,73,80],"captioning.":[8,65],"However,":[9],"existing":[10],"studies":[11],"have":[12],"shown":[13],"Transformer":[14,61],"has":[15],"a":[16],"problem":[17],"that":[18,36,147],"irrelevant":[19],"tokens":[20],"with":[21,29],"overlapping":[22],"neighbors":[23],"incorrectly":[24],"attend":[25],"to":[26,41,129,142,149,175],"each":[27],"other":[28],"relatively":[30],"large":[31],"attention":[32,127,134],"scores.":[33],"We":[34],"believe":[35],"this":[37,55],"limitation":[38],"is":[39,155],"due":[40],"incompleteness":[43],"of":[44,71,106,171],"Self-Attention":[46],"Network":[47,51,121],"(SAN)":[48],"and":[49,75,93,109,136,162],"Feed-Forward":[50],"(FFN).":[52],"To":[53],"solve":[54],"problem,":[56],"we":[57,83,116],"present":[58],"Full-Memory":[60],"method":[62,67,154],"for":[63],"improves":[68],"performance":[70,97],"both":[72,104],"encoding":[74,81],"language":[76,113],"decoding.":[77],"In":[78,111],"step,":[82,115],"propose":[84,117],"Full-LN":[86],"symmetric":[87],"structure,":[88],"which":[89,123],"enables":[90],"stable":[91],"training":[92],"better":[94],"model":[95,141],"generalization":[96],"by":[98],"symmetrically":[99],"embedding":[100],"Layer":[101],"Normalization":[102],"on":[103,144,157],"sides":[105],"SAN":[108],"FFN.":[110],"decoding":[114],"Memory":[119],"Attention":[120],"(MAN),":[122],"extends":[124],"traditional":[126],"mechanism":[128],"determine":[130],"correlation":[132],"between":[133],"results":[135],"input":[137],"sequences,":[138],"guiding":[139],"focus":[143],"words":[146],"need":[148],"be":[150],"attended":[151],"to.":[152],"Our":[153],"evaluated":[156],"MS":[159],"COCO":[160],"dataset":[161],"achieves":[163],"good":[164],"performance,":[165],"improving":[166],"result":[168],"terms":[170],"BLEU-4":[172],"from":[173],"38.4":[174],"39.3.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2023-01-10T00:00:00"}