{"id":"https://openalex.org/W4372337842","doi":"https://doi.org/10.1109/icassp49357.2023.10096424","title":"I-Tuning: Tuning Frozen Language Models with Image for Lightweight Image Captioning","display_name":"I-Tuning: Tuning Frozen Language Models with Image for Lightweight Image Captioning","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372337842","doi":"https://doi.org/10.1109/icassp49357.2023.10096424"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5055657033","display_name":"Ziyang Luo","orcid":"https://orcid.org/0000-0002-6037-0471"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ziyang Luo","raw_affiliation_strings":["Hong Kong Baptist University,Department of Computer Science,Hong Kong SAR,China","Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University,Department of Computer Science,Hong Kong SAR,China","institution_ids":["https://openalex.org/I141568987"]},{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112113390","display_name":"Zhipeng Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhipeng Hu","raw_affiliation_strings":["Zhejiang University,College of Computer Science and Technology,Hangzhou,China","College of Computer Science and Technology, Zhejiang University, Hangzhou, China","Fuxi AI Lab, NetEase Inc., Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Computer Science and Technology,Hangzhou,China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"Fuxi AI Lab, NetEase Inc., Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013796186","display_name":"Yadong Xi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yadong Xi","raw_affiliation_strings":["NetEase Inc.,Fuxi AI Lab,Hangzhou,China","Fuxi AI Lab, NetEase Inc., Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Inc.,Fuxi AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"Fuxi AI Lab, NetEase Inc., Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018408488","display_name":"Rongsheng Zhang","orcid":"https://orcid.org/0009-0008-1248-2090"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongsheng Zhang","raw_affiliation_strings":["NetEase Inc.,Fuxi AI Lab,Hangzhou,China","Fuxi AI Lab, NetEase Inc., Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Inc.,Fuxi AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"Fuxi AI Lab, NetEase Inc., Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034823980","display_name":"Jing Ma","orcid":"https://orcid.org/0000-0002-7464-8331"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jing Ma","raw_affiliation_strings":["Hong Kong Baptist University,Department of Computer Science,Hong Kong SAR,China","Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University,Department of Computer Science,Hong Kong SAR,China","institution_ids":["https://openalex.org/I141568987"]},{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I141568987"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9952999949455261,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9799000024795532,"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":0.9772534370422363},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8382932543754578},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6303147673606873},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5995787382125854},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.575547456741333},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5468953251838684},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.535470187664032},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.446304053068161},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4223487377166748},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.4135463237762451},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38768017292022705},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36540424823760986},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06786510348320007}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9772534370422363},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8382932543754578},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6303147673606873},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5995787382125854},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.575547456741333},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5468953251838684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.535470187664032},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.446304053068161},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4223487377166748},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.4135463237762451},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38768017292022705},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36540424823760986},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06786510348320007},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2123301721","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2904565150","https://openalex.org/W2908510526","https://openalex.org/W2964303773","https://openalex.org/W2997591391","https://openalex.org/W3035524453","https://openalex.org/W3091588028","https://openalex.org/W3104279398","https://openalex.org/W3166396011","https://openalex.org/W3167118264","https://openalex.org/W3174770825","https://openalex.org/W3193402170","https://openalex.org/W3209274285","https://openalex.org/W4307106676","https://openalex.org/W4313068342","https://openalex.org/W4385245566","https://openalex.org/W6678262379","https://openalex.org/W6739901393","https://openalex.org/W6757817989","https://openalex.org/W6759579507","https://openalex.org/W6789909235","https://openalex.org/W6791353385","https://openalex.org/W6800139874","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Image":[0],"Captioning":[1],"is":[2,93],"a":[3,47,55,63],"traditional":[4],"vision-and-language":[5],"task":[6],"that":[7,106],"aims":[8],"to":[9,41,68,86,124],"generate":[10],"the":[11,23,27,35,70,115],"language":[12,73],"description":[13],"of":[14,29,37,58],"an":[15],"image.":[16],"Recent":[17],"studies":[18],"focus":[19],"on":[20,100],"scaling":[21],"up":[22,123],"model":[24,38],"size":[25],"and":[26,76,95,130],"number":[28,57],"training":[30,136],"data,":[31],"which":[32,53],"significantly":[33],"increase":[34],"cost":[36],"training.":[39],"Different":[40],"these":[42],"heavy-cost":[43],"models,":[44],"we":[45],"introduce":[46],"lightweight":[48,94],"image":[49,102],"captioning":[50,103],"framework":[51,92],"(I-Tuning),":[52],"contains":[54],"small":[56],"trainable":[59,128],"parameters.":[60],"We":[61],"design":[62],"novel":[64],"I-Tuning":[65],"cross-attention":[66],"module":[67],"connect":[69],"non-trainable":[71],"pre-trained":[72],"decoder":[74],"GPT2":[75],"vision":[77],"encoder":[78],"CLIP-ViT.":[79],"Since":[80],"most":[81],"parameters":[82,129],"are":[83],"not":[84],"required":[85],"be":[87],"updated":[88],"during":[89],"training,":[90],"our":[91,107,120],"fast.":[96],"Experimental":[97],"results":[98],"conducted":[99],"three":[101],"benchmarks":[104],"reveal":[105],"frame-work":[108],"achieves":[109],"comparable":[110],"or":[111],"better":[112],"performance":[113],"than":[114],"large-scale":[116],"baseline":[117],"systems.":[118],"But":[119],"models":[121],"contain":[122],"10":[125],"times":[126],"fewer":[127,133],"require":[131],"much":[132],"data":[134],"for":[135],"compared":[137],"with":[138],"state-of-the-art":[139],"baselines.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}