{"id":"https://openalex.org/W4214917601","doi":"https://doi.org/10.1109/tcsvt.2022.3155795","title":"Adaptive Path Selection for Dynamic Image Captioning","display_name":"Adaptive Path Selection for Dynamic Image Captioning","publication_year":2022,"publication_date":"2022-03-02","ids":{"openalex":"https://openalex.org/W4214917601","doi":"https://doi.org/10.1109/tcsvt.2022.3155795"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2022.3155795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3155795","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-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 Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China"],"affiliations":[{"raw_affiliation_string":"Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701695","display_name":"Zhixin Li","orcid":null},"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 Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China"],"affiliations":[{"raw_affiliation_string":"Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087798028","display_name":"Zhenjun Tang","orcid":"https://orcid.org/0000-0003-3664-1363"},"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":"Zhenjun Tang","raw_affiliation_strings":["Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China"],"affiliations":[{"raw_affiliation_string":"Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","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"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Engineering, Northwest Normal University, Lanzhou, China","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":6.931,"has_fulltext":false,"cited_by_count":70,"citation_normalized_percentile":{"value":0.97927547,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"32","issue":"9","first_page":"5762","last_page":"5775"},"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":0.9994000196456909,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.8803347945213318},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8480615615844727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5944960713386536},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.580093264579773},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5052695870399475},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.49565351009368896},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.444233238697052},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.428450345993042},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4279431700706482},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41409921646118164},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3521319627761841},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2969249486923218}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8803347945213318},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8480615615844727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5944960713386536},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.580093264579773},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5052695870399475},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.49565351009368896},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.444233238697052},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.428450345993042},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4279431700706482},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41409921646118164},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3521319627761841},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2969249486923218},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2022.3155795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3155795","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1038957148","display_name":null,"funder_award_id":"61962008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"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/G3744706737","display_name":null,"funder_award_id":"61866004","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":81,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W956551720","https://openalex.org/W1514535095","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W2101105183","https://openalex.org/W2105103432","https://openalex.org/W2133512280","https://openalex.org/W2154652894","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2296385829","https://openalex.org/W2302086703","https://openalex.org/W2506483933","https://openalex.org/W2552002300","https://openalex.org/W2562731582","https://openalex.org/W2575842049","https://openalex.org/W2739542029","https://openalex.org/W2745461083","https://openalex.org/W2752782242","https://openalex.org/W2798581168","https://openalex.org/W2885013662","https://openalex.org/W2890531016","https://openalex.org/W2896006880","https://openalex.org/W2896457183","https://openalex.org/W2903617461","https://openalex.org/W2914163459","https://openalex.org/W2950014519","https://openalex.org/W2962861647","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963393494","https://openalex.org/W2966162142","https://openalex.org/W2966683369","https://openalex.org/W2974212192","https://openalex.org/W2978610144","https://openalex.org/W2979739834","https://openalex.org/W2979987972","https://openalex.org/W2981165461","https://openalex.org/W2986670728","https://openalex.org/W2987327987","https://openalex.org/W2990818246","https://openalex.org/W2995104385","https://openalex.org/W2998988444","https://openalex.org/W3012648429","https://openalex.org/W3018388102","https://openalex.org/W3034655362","https://openalex.org/W3034772996","https://openalex.org/W3035071066","https://openalex.org/W3035160838","https://openalex.org/W3035284526","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3080813890","https://openalex.org/W3096407995","https://openalex.org/W3102371147","https://openalex.org/W3106925514","https://openalex.org/W3113117059","https://openalex.org/W3128990302","https://openalex.org/W3134272453","https://openalex.org/W3136792391","https://openalex.org/W3155230099","https://openalex.org/W3162954998","https://openalex.org/W3174377922","https://openalex.org/W3175824375","https://openalex.org/W4205357838","https://openalex.org/W4288329833","https://openalex.org/W4385245566","https://openalex.org/W6682631176","https://openalex.org/W6739901393","https://openalex.org/W6741753902","https://openalex.org/W6745447533","https://openalex.org/W6750566404","https://openalex.org/W6755526309","https://openalex.org/W6763643401","https://openalex.org/W6768742326","https://openalex.org/W6772381481","https://openalex.org/W6774950721","https://openalex.org/W6785465245"],"related_works":["https://openalex.org/W2811390910","https://openalex.org/W2146076056","https://openalex.org/W2144059113","https://openalex.org/W3003836766","https://openalex.org/W1964120219","https://openalex.org/W2000165426","https://openalex.org/W2385132419","https://openalex.org/W2772780115","https://openalex.org/W2114557664","https://openalex.org/W2942471066"],"abstract_inverted_index":{"Image":[0],"captioning":[1],"is":[2,55,212],"a":[3,86,123,128,135,144,168,187],"challenging":[4],"task,":[5],"i.e.,":[6,98],"given":[7],"an":[8],"image":[9,190],"machine":[10],"automatically":[11],"generates":[12],"natural":[13],"language":[14],"that":[15,138,147,209],"matches":[16],"its":[17,203],"semantic":[18],"content":[19],"and":[20,35,57,59,68,113,143,184,193],"has":[21],"attracted":[22],"much":[23],"attention":[24],"in":[25,116,127],"recent":[26],"years.":[27],"However,":[28],"most":[29],"existing":[30],"models":[31],"are":[32],"designed":[33],"manually,":[34],"their":[36],"performance":[37],"depends":[38],"heavily":[39],"on":[40,159],"the":[41,45,49,53,64,76,79,91,140,152,156,160,200],"expert":[42],"experience":[43],"of":[44,52,78,108],"designer.":[46],"In":[47,81],"addition,":[48],"computational":[50],"flow":[51],"model":[54,165],"predefined,":[56],"hard":[58],"easy":[60],"samples":[61],"will":[62],"share":[63],"same":[65],"coding":[66],"path":[67],"easily":[69],"interfere":[70],"with":[71],"each":[72,119],"other,":[73],"thus":[74],"confusing":[75],"learning":[77],"model.":[80],"this":[82],"paper,":[83],"we":[84,103],"propose":[85],"Dynamic":[87],"Transformer":[88],"to":[89,96,121,149,154,198,215],"change":[90],"encoding":[92],"procedure":[93],"from":[94],"sequential":[95],"adaptive,":[97],"data-dependent":[99],"computing":[100],"paths.":[101,178],"Specifically,":[102],"design":[104],"three":[105],"different":[106],"types":[107],"visual":[109,170,175],"feature":[110,176],"extraction":[111,177],"blocks":[112],"deploy":[114],"them":[115],"parallel":[117],"at":[118],"layer":[120],"construct":[122],"multi-layer":[124],"routing":[125,145],"space":[126],"fully":[129],"connected":[130],"manner.":[131],"Each":[132],"block":[133],"contains":[134],"calculation":[136],"unit":[137],"performs":[139],"corresponding":[141],"operations":[142],"gate":[146],"learns":[148],"adaptively":[150],"select":[151],"direction":[153],"pass":[155],"signal":[157],"based":[158],"input":[161],"image.":[162],"Thus,":[163],"our":[164,181,210],"can":[166],"achieve":[167],"robust":[169],"representation":[171],"by":[172],"exploring":[173],"potential":[174],"We":[179],"evaluate":[180],"method":[182,211],"quantitatively":[183],"qualitatively":[185],"using":[186],"benchmark":[188],"MSCOCO":[189],"caption":[191],"dataset":[192],"perform":[194],"extensive":[195],"ablation":[196],"studies":[197],"investigate":[199],"reasons":[201],"behind":[202],"effectiveness.":[204],"The":[205],"experimental":[206],"results":[207],"show":[208],"significantly":[213],"superior":[214],"previous":[216],"state-of-the-art":[217],"methods.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-31T07:56:22.981413","created_date":"2025-10-10T00:00:00"}