{"id":"https://openalex.org/W4402352504","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650602","title":"CLIP-Driven Low-Cost Image Captioning","display_name":"CLIP-Driven Low-Cost Image Captioning","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352504","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650602"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5002975903","display_name":"Yiyu Wang","orcid":"https://orcid.org/0000-0003-0329-6911"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiyu Wang","raw_affiliation_strings":["University of Chinese Academy of Sciences,Beijing,China,101408"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Beijing,China,101408","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051136267","display_name":"Junguo Xu","orcid":"https://orcid.org/0009-0008-6297-8924"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jungang Xu","raw_affiliation_strings":["University of Chinese Academy of Sciences,Beijing,China,101408"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Beijing,China,101408","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103211417","display_name":"Yingfei Sun","orcid":"https://orcid.org/0000-0003-0615-2569"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingfei Sun","raw_affiliation_strings":["University of Chinese Academy of Sciences,Beijing,China,101408"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Beijing,China,101408","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":1.0527,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82082727,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9976999759674072,"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":0.9912999868392944,"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":0.9496682286262512},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7245674133300781},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5862140655517578},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3398451805114746},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33036381006240845}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9496682286262512},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7245674133300781},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5862140655517578},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3398451805114746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33036381006240845}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2105482032","https://openalex.org/W2194775991","https://openalex.org/W2506483933","https://openalex.org/W2745461083","https://openalex.org/W2892213699","https://openalex.org/W2947912915","https://openalex.org/W2950635152","https://openalex.org/W2963084599","https://openalex.org/W2965697393","https://openalex.org/W2986670728","https://openalex.org/W2996677910","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3035463379","https://openalex.org/W3093394956","https://openalex.org/W3124149278","https://openalex.org/W3138516171","https://openalex.org/W3174046981","https://openalex.org/W3174377922","https://openalex.org/W3175824375","https://openalex.org/W3205981128","https://openalex.org/W3210150990","https://openalex.org/W4221147537","https://openalex.org/W4288089799","https://openalex.org/W4292828275","https://openalex.org/W4293363567","https://openalex.org/W4307106676","https://openalex.org/W4367674159","https://openalex.org/W4375868765","https://openalex.org/W4376852293","https://openalex.org/W4382460199","https://openalex.org/W4385245566","https://openalex.org/W4385482940","https://openalex.org/W4385482983","https://openalex.org/W4385567053","https://openalex.org/W4386566587","https://openalex.org/W6637373629","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6746208923","https://openalex.org/W6763643401","https://openalex.org/W6766978945","https://openalex.org/W6769627184","https://openalex.org/W6784333009","https://openalex.org/W6791353385","https://openalex.org/W6851149231"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Image":[0],"captioning,":[1],"as":[2,39],"a":[3,40,89,117,127],"typical":[4],"multi-modal":[5],"task,":[6],"has":[7,12,21],"received":[8],"increasing":[9],"attention":[10],"and":[11,82,91,99,125],"made":[13],"significant":[14],"progress.":[15],"Recently,":[16],"the":[17,33,51,63,111,142,147,167],"proposal":[18],"of":[19,57,149,169],"CLIP":[20,38,143],"shown":[22],"strong":[23],"application":[24],"potential":[25,48],"in":[26],"various":[27],"tasks,":[28],"including":[29],"image":[30,106],"captioning.":[31],"However,":[32],"current":[34],"approaches":[35],"simply":[36],"employ":[37],"visual":[41,113],"feature":[42,132],"extractor":[43],"without":[44],"fully":[45,95],"utilizing":[46],"its":[47,150,156],"benefits":[49],"from":[50],"contrastive":[52],"learning":[53],"paradigm.":[54],"Furthermore,":[55,134],"most":[56],"them":[58],"are":[59],"resource-expensive":[60],"due":[61],"to":[62,101,104,121,154],"need":[64],"for":[65,70,78,131],"additional":[66,74],"large-scale":[67],"image-text":[68],"datasets":[69],"incremental":[71],"pre-training":[72],"or":[73],"pre-trained":[75],"language":[76],"models":[77],"captioning":[79,107,136],"decoder":[80,137],"initialization":[81],"finetuning.":[83],"In":[84],"this":[85],"paper,":[86],"we":[87,115],"propose":[88],"simple":[90],"effective":[92],"approach":[93],"that":[94],"utilizes":[96],"CLIP\u2019s":[97],"properties":[98],"advantages":[100],"transfer":[102],"it":[103],"an":[105],"model.":[108],"Specifically,":[109],"following":[110],"obtained":[112],"features,":[114],"design":[116,126],"memory":[118],"retrieval":[119],"module":[120,130],"introduce":[122],"more":[123],"information":[124],"joint":[128],"representation":[129],"enhancement.":[133],"our":[135,170],"is":[138],"constructed":[139],"based":[140],"on":[141,163],"text":[144],"encoder":[145],"with":[146],"reuse":[148],"parameters,":[151],"which":[152],"aims":[153],"leverage":[155],"priori":[157],"textual":[158],"embedding":[159],"knowledge.":[160],"Experimental":[161],"results":[162],"MSCOCO":[164],"dataset":[165],"verify":[166],"effectiveness":[168],"proposal.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}