{"id":"https://openalex.org/W4283722434","doi":"https://doi.org/10.1109/tnnls.2022.3185320","title":"Adaptive Semantic-Enhanced Transformer for Image Captioning","display_name":"Adaptive Semantic-Enhanced Transformer for Image Captioning","publication_year":2022,"publication_date":"2022-06-29","ids":{"openalex":"https://openalex.org/W4283722434","doi":"https://doi.org/10.1109/tnnls.2022.3185320","pmid":"https://pubmed.ncbi.nlm.nih.gov/35767480"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2022.3185320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3185320","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100345320","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0001-6270-7771"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["Department of Computer Science and Technology, East China University of Science and Technology, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6270-7771","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082310234","display_name":"Zhongjun Fang","orcid":"https://orcid.org/0000-0003-2978-1384"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongjun Fang","raw_affiliation_strings":["Department of Computer Science and Technology, East China University of Science and Technology, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2978-1384","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100700666","display_name":"Han Sun","orcid":"https://orcid.org/0009-0002-8186-2376"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Sun","raw_affiliation_strings":["Department of Computer Science and Technology, East China University of Science and Technology, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100621319","display_name":"Zhe Wang","orcid":"https://orcid.org/0000-0002-3759-2041"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Wang","raw_affiliation_strings":["Department of Computer Science and Technology, East China University of Science and Technology, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3759-2041","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100345320"],"corresponding_institution_ids":["https://openalex.org/I143593769"],"apc_list":null,"apc_paid":null,"fwci":4.9748,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.96464729,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"35","issue":"2","first_page":"1785","last_page":"1796"},"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":0.9939000010490417,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9858999848365784,"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":0.9168154001235962},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8378173112869263},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6424090266227722},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6178628206253052},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5658292174339294},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4988377094268799},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32594388723373413},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2082841396331787},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08542504906654358}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9168154001235962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8378173112869263},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6424090266227722},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6178628206253052},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5658292174339294},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4988377094268799},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32594388723373413},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2082841396331787},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08542504906654358},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/tnnls.2022.3185320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3185320","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:35767480","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35767480","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6893319343","display_name":null,"funder_award_id":"22ZR1418400","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1686810756","https://openalex.org/W1773149199","https://openalex.org/W1785460851","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1903029394","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2302086703","https://openalex.org/W2506483933","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2558834163","https://openalex.org/W2560645892","https://openalex.org/W2575842049","https://openalex.org/W2740118378","https://openalex.org/W2745461083","https://openalex.org/W2754927243","https://openalex.org/W2795151422","https://openalex.org/W2808206191","https://openalex.org/W2890531016","https://openalex.org/W2891571621","https://openalex.org/W2906314281","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2964018924","https://openalex.org/W2965597639","https://openalex.org/W2968831808","https://openalex.org/W2973642807","https://openalex.org/W2974212192","https://openalex.org/W2981165461","https://openalex.org/W2983141445","https://openalex.org/W2986670728","https://openalex.org/W2990818246","https://openalex.org/W2996202528","https://openalex.org/W2996421194","https://openalex.org/W3034655362","https://openalex.org/W3035160838","https://openalex.org/W3035284526","https://openalex.org/W3036848992","https://openalex.org/W3103651098","https://openalex.org/W3107503524","https://openalex.org/W3173220247","https://openalex.org/W3175824375","https://openalex.org/W6600334730","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638167273","https://openalex.org/W6678262379","https://openalex.org/W6679434410","https://openalex.org/W6682631176","https://openalex.org/W6684191040","https://openalex.org/W6739901393","https://openalex.org/W6763643401","https://openalex.org/W6767200354"],"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":{"In":[0],"the":[1,36,42,55,85,92,107,114,134,143,151,155,186,210],"research":[2],"on":[3,185],"image":[4,68],"captioning,":[5],"rich":[6],"semantic":[7,21,29,49,71,86,104,115,121,139,206,214,226],"information":[8,22,51,73,140,207,217],"is":[9,179],"very":[10],"important":[11],"for":[12,67,120,142,182],"generating":[13],"critical":[14],"caption":[15,148],"words":[16],"as":[17],"guiding":[18,50],"information.":[19],"However,":[20],"from":[23,106,170],"offline":[24],"object":[25],"detectors":[26],"involves":[27],"many":[28],"objects":[30,105],"that":[31,178,198],"do":[32],"not":[33],"appear":[34],"in":[35,191],"caption,":[37],"thereby":[38],"bringing":[39],"noise":[40],"into":[41],"decoding":[43,56,173],"process.":[44],"To":[45],"produce":[46],"more":[47,144,180,221],"accurate":[48,145,222],"and":[52,138,158,174,194,208,215,229],"further":[53],"optimize":[54],"process,":[57],"we":[58,75,124],"propose":[59,76,125],"an":[60,126],"end-to-end":[61],"adaptive":[62,127,167],"semantic-enhanced":[63],"transformer":[64],"(AS-Transformer)":[65],"model":[66,163],"captioning.":[69],"For":[70],"enhancement":[72,122,168,227],"extraction,":[74],"a":[77,98,165],"constrained":[78],"weaklysupervised":[79],"learning":[80,95],"(CWSL)":[81],"module,":[82,160],"which":[83,219],"reconstructs":[84],"object's":[87],"probability":[88,109],"distribution":[89,110],"detected":[90],"by":[91],"multiple":[93],"instances":[94],"(MIL)":[96],"through":[97],"joint":[99,152],"loss":[100],"function.":[101],"These":[102],"strengthened":[103],"reconstructed":[108],"can":[111,202],"better":[112],"depict":[113],"meaning":[116],"of":[117,147,154],"images.":[118],"Also,":[119],"decoding,":[123],"gated":[128],"mechanism":[129,169],"(AGM)":[130],"module":[131,157],"to":[132,172],"adjust":[133,209],"attention":[135,211],"between":[136,213],"visual":[137,176,216],"adaptively":[141,203],"generation":[146],"words.":[149],"Through":[150],"control":[153],"CWSL":[156],"AGM":[159],"our":[161,199],"proposed":[162,200],"constructs":[164],"complete":[166],"encoding":[171],"obtains":[175],"context":[177],"suitable":[181],"captions.":[183],"Experiments":[184],"public":[187],"Microsoft":[188],"Common":[189],"Objects":[190],"COntext":[192],"(MSCOCO)":[193],"Flickr30K":[195],"datasets":[196],"illustrate":[197],"AS-Transformer":[201],"obtain":[204],"effective":[205],"weights":[212],"automatically,":[218],"achieves":[220],"captions":[223],"compared":[224],"with":[225],"methods":[228],"outperforms":[230],"state-of-the-art":[231],"methods.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":8}],"updated_date":"2026-05-17T08:19:37.847499","created_date":"2025-10-10T00:00:00"}