{"id":"https://openalex.org/W4385488757","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191656","title":"Image Alone Are Not Enough: A General Semantic-Augmented Transformer-Based Framework for Image Captioning","display_name":"Image Alone Are Not Enough: A General Semantic-Augmented Transformer-Based Framework for Image Captioning","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385488757","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191656"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191656","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5100320740","display_name":"Jiawei Liu","orcid":"https://orcid.org/0000-0002-0157-9339"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiawei Liu","raw_affiliation_strings":["East China Normal University,Shanghai,China","East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398281","display_name":"Xin Lin","orcid":"https://orcid.org/0000-0001-6913-4654"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Lin","raw_affiliation_strings":["East China Normal University,Shanghai,China","East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010540039","display_name":"Liang He","orcid":"https://orcid.org/0000-0002-4723-5486"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["East China Normal University,Shanghai,China","East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100320740"],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08204435,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"01","last_page":"08"},"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":0.9919999837875366,"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":0.9850999712944031,"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":0.9041361808776855},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7884559631347656},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7154269218444824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.561331033706665},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4955354928970337},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.49054569005966187},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4647933840751648},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4535178244113922},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.419344425201416},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3844931721687317},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1258571445941925}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9041361808776855},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7884559631347656},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7154269218444824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.561331033706665},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4955354928970337},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.49054569005966187},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4647933840751648},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4535178244113922},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.419344425201416},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3844931721687317},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1258571445941925},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191656","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2130942839","https://openalex.org/W2154652894","https://openalex.org/W2506483933","https://openalex.org/W2558834163","https://openalex.org/W2560645892","https://openalex.org/W2575842049","https://openalex.org/W2600463316","https://openalex.org/W2745461083","https://openalex.org/W2754927243","https://openalex.org/W2890531016","https://openalex.org/W2896348597","https://openalex.org/W2896457183","https://openalex.org/W2901988662","https://openalex.org/W2952122856","https://openalex.org/W2963101956","https://openalex.org/W2965697393","https://openalex.org/W2972897806","https://openalex.org/W2986670728","https://openalex.org/W2990818246","https://openalex.org/W2992478697","https://openalex.org/W3034655362","https://openalex.org/W3034984754","https://openalex.org/W3035284526","https://openalex.org/W3035497460","https://openalex.org/W3167939936","https://openalex.org/W3174377922","https://openalex.org/W3182293212","https://openalex.org/W3205071568","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6678262379","https://openalex.org/W6679436768","https://openalex.org/W6682631176","https://openalex.org/W6755207826","https://openalex.org/W6798308576"],"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],"has":[2],"long":[3],"been":[4],"widely":[5],"regarded":[6],"as":[7,134],"a":[8,79],"modal":[9],"transformation":[10,24,88],"task":[11],"from":[12],"visual":[13,30,41],"to":[14,37,53,68,85,105,112,119,137,141,145,154],"linguistic":[15,44],"modality.":[16],"Most":[17],"current":[18],"research":[19],"focuses":[20],"on":[21,166,179],"the":[22,38,59,66,90,94,99,108,114,120,125,128,139,146,149,155,180],"information":[23,54,131],"between":[25,40,89],"single":[26],"modalities":[27],"dominated":[28],"by":[29],"features,":[31],"while":[32],"less":[33],"attention":[34,144],"is":[35,51,132],"paid":[36],"interaction":[39],"features":[42,111],"and":[43,56,71],"features.":[45],"This":[46],"rigid":[47],"single-modal":[48],"conversion":[49,60],"method":[50],"prone":[52],"confusion":[55],"loss":[57],"during":[58],"process,":[61],"making":[62],"it":[63],"difficult":[64],"for":[65,158],"model":[67,140],"generate":[69],"accurate":[70],"detailed":[72],"captions.":[73,160],"In":[74,93,124],"this":[75],"paper,":[76],"we":[77,97],"propose":[78],"general":[80],"Semantic-Augmented":[81],"Transformer-Based":[82],"(SAT)":[83],"framework":[84,165],"facilitate":[86],"smoother":[87],"two":[91],"modalities.":[92],"encoding":[95],"stage,":[96,127],"use":[98],"fine-grained":[100,159],"description":[101],"of":[102],"each":[103],"region":[104],"fuse":[106],"with":[107],"corresponding":[109],"image":[110,115,150],"make":[113],"feature":[116,122],"representation":[117],"closer":[118],"text":[121],"representation.":[123],"decoding":[126],"caption's":[129],"part-of-speech":[130],"used":[133],"prior":[135],"knowledge":[136],"constrain":[138],"pay":[142],"more":[143],"details":[147],"in":[148],"rather":[151],"than":[152],"only":[153],"prominent":[156],"entities":[157],"We":[161],"extensively":[162],"evaluate":[163],"our":[164,184],"various":[167],"state-of-the-art":[168],"transformer-based":[169],"models.":[170],"Experiments":[171],"demonstrate":[172],"that":[173],"these":[174],"models":[175],"have":[176],"superior":[177],"performance":[178],"MS-COCO":[181],"dataset":[182],"under":[183],"framework.":[185]},"counts_by_year":[],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}