{"id":"https://openalex.org/W4293518257","doi":"https://doi.org/10.1109/icme52920.2022.9859885","title":"Dynamic Transformer for Image Captioning","display_name":"Dynamic Transformer for Image Captioning","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4293518257","doi":"https://doi.org/10.1109/icme52920.2022.9859885"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859885","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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/A5060117326","display_name":"Tiantao Xian","orcid":"https://orcid.org/0000-0002-1092-9732"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tiantao Xian","raw_affiliation_strings":["Guangxi Normal University,Guangxi Key Lab of Multi-source Information Mining and Security,Guilin,China,541004"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,Guangxi Key Lab of Multi-source Information Mining and Security,Guilin,China,541004","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701695","display_name":"Zhixin Li","orcid":"https://orcid.org/0000-0002-5313-6134"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixin Li","raw_affiliation_strings":["Guangxi Normal University,Guangxi Key Lab of Multi-source Information Mining and Security,Guilin,China,541004"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,Guangxi Key Lab of Multi-source Information Mining and Security,Guilin,China,541004","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371624","display_name":"Tianyu Chen","orcid":"https://orcid.org/0000-0002-5101-7561"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyu Chen","raw_affiliation_strings":["Guangxi Normal University,Guangxi Key Lab of Multi-source Information Mining and Security,Guilin,China,541004"],"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,Guangxi Key Lab of Multi-source Information Mining and Security,Guilin,China,541004","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053794277","display_name":"Huifang Ma","orcid":"https://orcid.org/0000-0002-5104-8982"},"institutions":[{"id":"https://openalex.org/I68986083","display_name":"Northwest Normal University","ror":"https://ror.org/00gx3j908","country_code":"CN","type":"education","lineage":["https://openalex.org/I68986083"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huifang Ma","raw_affiliation_strings":["College of Computer Science and Engineering, Northwest Normal University,Lanzhou,China,730070"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Engineering, Northwest Normal University,Lanzhou,China,730070","institution_ids":["https://openalex.org/I68986083"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5060117326"],"corresponding_institution_ids":["https://openalex.org/I29739308"],"apc_list":null,"apc_paid":null,"fwci":0.06,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.26372451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9968000054359436,"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":0.9947999715805054,"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":0.88309645652771},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7996087670326233},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6868881583213806},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5343522429466248},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4362713694572449},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4258565902709961},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.4117773771286011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38577818870544434},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3618660569190979},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.15413600206375122},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10558795928955078}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.88309645652771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7996087670326233},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6868881583213806},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5343522429466248},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4362713694572449},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4258565902709961},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.4117773771286011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38577818870544434},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3618660569190979},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.15413600206375122},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10558795928955078},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9859885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859885","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1153685412","display_name":null,"funder_award_id":"61966004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6096834954","display_name":null,"funder_award_id":"2019GXNSFDA245018","funder_id":"https://openalex.org/F4320322768","funder_display_name":"Natural Science Foundation of Guangxi Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322768","display_name":"Natural Science Foundation of Guangxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2194775991","https://openalex.org/W2506483933","https://openalex.org/W2745461083","https://openalex.org/W2896457183","https://openalex.org/W2952688802","https://openalex.org/W2963101956","https://openalex.org/W2986670728","https://openalex.org/W2990818246","https://openalex.org/W3012648429","https://openalex.org/W3034655362","https://openalex.org/W3035071066","https://openalex.org/W3035160838","https://openalex.org/W3113117059","https://openalex.org/W3155230099","https://openalex.org/W3162954998","https://openalex.org/W3172393158","https://openalex.org/W3175824375","https://openalex.org/W4205357838","https://openalex.org/W4385245566","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6739901393","https://openalex.org/W6754778999","https://openalex.org/W6755207826","https://openalex.org/W6774950721","https://openalex.org/W6785465245","https://openalex.org/W6787735275"],"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":{"Transformer-based":[0],"architectures":[1],"have":[2],"shown":[3],"great":[4],"success":[5],"in":[6,90,101],"image":[7,130],"captioning.":[8],"However,":[9],"the":[10,14,38,66,75,79,83,128],"calculation":[11,62],"process":[12],"of":[13,55],"model":[15,114],"is":[16,19],"predefined,":[17],"which":[18],"heavily":[20],"dependent":[21],"on":[22,82,127,141],"expert":[23],"experience":[24],"and":[25,69,133],"lacks":[26],"flexibility.":[27],"In":[28,106],"this":[29],"paper,":[30],"we":[31,50,108],"propose":[32],"a":[33,61,70,97,102,110],"Dynamic":[34],"Transformer":[35],"to":[36,43,64,73,77,95,115],"change":[37],"encoding":[39],"procedure":[40],"from":[41],"sequential":[42],"adaptive,":[44],"i.e.,":[45,138],"data-dependent":[46],"computing":[47],"paths.":[48],"Specifically,":[49],"design":[51],"three":[52],"different":[53],"types":[54],"feature":[56],"extraction":[57],"blocks,":[58],"each":[59,93],"containing":[60],"unit":[63],"perform":[65],"corresponding":[67],"operation":[68],"routing":[71,99],"gate":[72],"select":[74],"direction":[76],"pass":[78],"signal":[80],"based":[81],"input":[84],"data.":[85],"Three":[86],"blocks":[87],"are":[88],"deployed":[89],"parallel":[91],"at":[92],"layer":[94],"build":[96],"multi-layer":[98],"space":[100],"fully":[103],"connected":[104],"manner.":[105],"addition,":[107],"use":[109],"path":[111],"regularization":[112],"constraint":[113],"learn":[116],"similar":[117,121],"paths":[118],"for":[119],"semantically":[120],"images.":[122],"We":[123],"conduct":[124],"extensive":[125],"experiments":[126],"COCO":[129],"captioning":[131],"dataset":[132],"achieve":[134],"new":[135],"state-of-the-art":[136],"performance,":[137],"133.2%":[139],"CIDEr":[140],"Karpathy":[142],"test":[143],"split.":[144]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}