{"id":"https://openalex.org/W4386148430","doi":"https://doi.org/10.1145/3581783.3611891","title":"CgT-GAN: CLIP-guided Text GAN for Image Captioning","display_name":"CgT-GAN: CLIP-guided Text GAN for Image Captioning","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4386148430","doi":"https://doi.org/10.1145/3581783.3611891"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611891","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.12045","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102548773","display_name":"Jiarui Yu","orcid":"https://orcid.org/0000-0001-6327-6811"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiarui Yu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103325586","display_name":"Haoran Li","orcid":"https://orcid.org/0009-0007-3593-7169"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Li","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043525989","display_name":"Yanbin Hao","orcid":"https://orcid.org/0000-0002-0695-1566"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanbin Hao","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065767090","display_name":"Bin Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bin Zhu","raw_affiliation_strings":["Singapore Management University, Bras Basah, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore Management University, Bras Basah, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025292786","display_name":"Tong Xu","orcid":"https://orcid.org/0000-0003-4246-5386"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Xu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038668215","display_name":"Xiangnan He","orcid":"https://orcid.org/0000-0001-8472-7992"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangnan He","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102548773"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":2.997,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.93083148,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2252","last_page":"2263"},"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":0.9887999892234802,"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":0.9835000038146973,"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":0.8595048189163208},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8073384761810303},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.7554543614387512},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5682972073554993},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5595083832740784},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5452679991722107},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5196386575698853},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5166966915130615},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5114840269088745},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4822326600551605},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4730184078216553},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.42070209980010986},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.41335758566856384},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38143670558929443},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14729663729667664}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8595048189163208},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8073384761810303},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.7554543614387512},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5682972073554993},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5595083832740784},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5452679991722107},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5196386575698853},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5166966915130615},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5114840269088745},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4822326600551605},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4730184078216553},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.42070209980010986},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.41335758566856384},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38143670558929443},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14729663729667664},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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":3,"locations":[{"id":"doi:10.1145/3581783.3611891","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2308.12045","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.12045","pdf_url":"https://arxiv.org/pdf/2308.12045","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-10015","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/9012","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1145/3581783.3611891","raw_type":"Conference Proceeding Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.12045","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.12045","pdf_url":"https://arxiv.org/pdf/2308.12045","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1111288224","display_name":null,"funder_award_id":"2020YFB1406703","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386148430.pdf","grobid_xml":"https://content.openalex.org/works/W4386148430.grobid-xml"},"referenced_works_count":79,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1514535095","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2154652894","https://openalex.org/W2425121537","https://openalex.org/W2463955103","https://openalex.org/W2506483933","https://openalex.org/W2550553598","https://openalex.org/W2557728737","https://openalex.org/W2568262903","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2803525166","https://openalex.org/W2886641317","https://openalex.org/W2890531016","https://openalex.org/W2908510526","https://openalex.org/W2948037078","https://openalex.org/W2962968835","https://openalex.org/W2963048642","https://openalex.org/W2963084599","https://openalex.org/W2963536419","https://openalex.org/W2963743213","https://openalex.org/W2964268978","https://openalex.org/W2965373594","https://openalex.org/W2981994675","https://openalex.org/W2990307191","https://openalex.org/W2992478697","https://openalex.org/W3004328990","https://openalex.org/W3034493371","https://openalex.org/W3034667500","https://openalex.org/W3035284526","https://openalex.org/W3086385316","https://openalex.org/W3094502228","https://openalex.org/W3096831136","https://openalex.org/W3101313921","https://openalex.org/W3126337491","https://openalex.org/W3135254306","https://openalex.org/W3152980002","https://openalex.org/W3153469116","https://openalex.org/W3160190143","https://openalex.org/W3166396011","https://openalex.org/W3177493543","https://openalex.org/W3193402170","https://openalex.org/W3193917007","https://openalex.org/W3205021045","https://openalex.org/W4205260486","https://openalex.org/W4214657742","https://openalex.org/W4214926101","https://openalex.org/W4224035735","https://openalex.org/W4225432580","https://openalex.org/W4226117651","https://openalex.org/W4281686064","https://openalex.org/W4281699561","https://openalex.org/W4282920689","https://openalex.org/W4282968790","https://openalex.org/W4283793919","https://openalex.org/W4285191490","https://openalex.org/W4287107550","https://openalex.org/W4287197062","https://openalex.org/W4289542422","https://openalex.org/W4292828275","https://openalex.org/W4307106676","https://openalex.org/W4309398562","https://openalex.org/W4312320490","https://openalex.org/W4312480274","https://openalex.org/W4312708649","https://openalex.org/W4312938727","https://openalex.org/W4320339901","https://openalex.org/W4322615526","https://openalex.org/W4323570346","https://openalex.org/W4363672019","https://openalex.org/W4364302332","https://openalex.org/W4385245566","https://openalex.org/W4385567053","https://openalex.org/W6600553734"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2029561777","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W172797710","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403"],"abstract_inverted_index":{"The":[0,114],"large-scale":[1],"visual-language":[2],"pre-trained":[3],"model,":[4],"Contrastive":[5],"Language-Image":[6],"Pre-training":[7],"(CLIP),":[8],"has":[9],"significantly":[10,198],"improved":[11],"image":[12,23],"captioning":[13,24],"for":[14,53],"scenarios":[15],"without":[16,25],"human-annotated":[17],"image-caption":[18],"pairs.":[19],"Recent":[20],"advanced":[21],"CLIP-based":[22,108,141],"human":[26,126],"annotations":[27],"follows":[28],"a":[29,160,173],"text-only":[30],"training":[31,79,94],"paradigm,":[32],"i.e.,":[33],"reconstructing":[34],"text":[35,54,71,105,175],"from":[36,129],"shared":[37],"embedding":[38,176],"space.":[39],"Nevertheless,":[40],"these":[41],"approaches":[42],"are":[43],"limited":[44],"by":[45,139,177],"the":[46,65,78,83,100,122,130,134,140,147,151,169,180],"training/inference":[47],"gap":[48],"or":[49],"huge":[50],"storage":[51],"requirements":[52],"embeddings.":[55],"Given":[56],"that":[57,193],"it":[58],"is":[59,117,203],"trivial":[60],"to":[61,81,85,95,98,110,125,146],"obtain":[62],"images":[63,76],"in":[64],"real":[66,87],"world,":[67],"we":[68,91,157],"propose":[69],"CLIP-guided":[70],"GAN":[72],"(CgT-GAN),":[73],"which":[74,167],"incorporates":[75],"into":[77],"process":[80],"enable":[82],"model":[84],"\"see\"":[86],"visual":[88],"modality.":[89],"Particularly,":[90],"use":[92],"adversarial":[93],"teach":[96],"CgT-GAN":[97,194],"mimic":[99],"phrases":[101],"of":[102],"an":[103],"external":[104],"corpus":[106],"and":[107,133,190],"reward":[109,137,142,154,164],"provide":[111],"semantic":[112,135,152,162],"guidance.":[113],"caption":[115,123,171],"generator":[116],"jointly":[118],"rewarded":[119],"based":[120],"on":[121,185],"naturalness":[124],"language":[127],"calculated":[128],"GAN's":[131],"discriminator":[132],"guidance":[136,153,163],"computed":[138],"module.":[143],"In":[144],"addition":[145],"cosine":[148],"similarity":[149],"as":[150],"(i.e.,":[155],"CLIP-cos),":[156],"further":[158],"introduce":[159],"novel":[161],"called":[165],"CLIP-agg,":[166],"aligns":[168],"generated":[170],"with":[172],"weighted":[174],"attentively":[178],"aggregating":[179],"entire":[181],"corpus.":[182],"Experimental":[183],"results":[184],"three":[186],"subtasks":[187],"(ZS-IC,":[188],"In-UIC":[189],"Cross-UIC)":[191],"show":[192],"outperforms":[195],"state-of-the-art":[196],"methods":[197],"across":[199],"all":[200],"metrics.":[201],"Code":[202],"available":[204],"at":[205],"https://github.com/Lihr747/CgtGAN.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":11}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}