{"id":"https://openalex.org/W4393302608","doi":"https://doi.org/10.1145/3640771.3640783","title":"CLIP-M-Cap: CLIP Mean Teacher for Image Captioning","display_name":"CLIP-M-Cap: CLIP Mean Teacher for Image Captioning","publication_year":2023,"publication_date":"2023-10-13","ids":{"openalex":"https://openalex.org/W4393302608","doi":"https://doi.org/10.1145/3640771.3640783"},"language":"en","primary_location":{"id":"doi:10.1145/3640771.3640783","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3640771.3640783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 2nd International Symposium on Computing and Artificial Intelligence","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/A5052089729","display_name":"Shuo Chen","orcid":"https://orcid.org/0009-0002-4596-6709"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuo Chen","raw_affiliation_strings":["Shanghai university of engineering science, China"],"affiliations":[{"raw_affiliation_string":"Shanghai university of engineering science, China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5117428678","display_name":"Juan Zhang","orcid":"https://orcid.org/0000-0003-1558-1656"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juan Zhang","raw_affiliation_strings":["Shanghai university of engineering science, China"],"affiliations":[{"raw_affiliation_string":"Shanghai university of engineering science, China","institution_ids":["https://openalex.org/I141962983"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5052089729"],"corresponding_institution_ids":["https://openalex.org/I141962983"],"apc_list":null,"apc_paid":null,"fwci":0.1236,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47609023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"50","last_page":"55"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.996399998664856,"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":0.9830999970436096,"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":0.9472274780273438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.665176510810852},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5666420459747314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44274190068244934},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42791467905044556},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.33256226778030396}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9472274780273438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.665176510810852},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5666420459747314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44274190068244934},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42791467905044556},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.33256226778030396}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3640771.3640783","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3640771.3640783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 2nd International Symposium on Computing and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1676314349","https://openalex.org/W1773149199","https://openalex.org/W1956340063","https://openalex.org/W1981276685","https://openalex.org/W2624972355","https://openalex.org/W2745461083","https://openalex.org/W2896348597","https://openalex.org/W3139408490","https://openalex.org/W4225832925","https://openalex.org/W4245835284","https://openalex.org/W4292828275","https://openalex.org/W4312922092","https://openalex.org/W6600336842","https://openalex.org/W6601804787"],"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":{"Abstract.":[0],"Image":[1],"description":[2],"plays":[3],"a":[4,52,66],"pivotal":[5],"role":[6],"in":[7,149],"the":[8,46,69,77,94,101,107,113,132],"realm":[9],"of":[10,61,82,103,109,134],"computer":[11],"vision":[12],"language":[13],"tasks,":[14],"as":[15,65],"its":[16],"core":[17],"mission":[18],"revolves":[19],"around":[20],"predicting":[21],"relevant":[22],"textual":[23],"information":[24],"given":[25],"an":[26,35],"input":[27],"image.":[28],"In":[29,76,93],"this":[30,41],"research":[31],"paper,":[32],"we":[33,50,85,99,116,129],"introduce":[34],"innovative":[36],"model":[37,120,137],"(Clip-M-cap)":[38],"to":[39,88,105],"tackle":[40],"challenge.":[42],"Drawing":[43],"inspiration":[44],"from":[45],"Mean":[47],"Teacher":[48],"approach,":[49],"present":[51],"fresh":[53],"network":[54],"architecture":[55],"that":[56],"comprises":[57],"two":[58,122],"branches.":[59],"One":[60],"these":[62],"branches":[63],"acts":[64],"reference":[67],"for":[68],"other,":[70],"providing":[71],"essential":[72],"support":[73],"during":[74],"training.":[75],"image":[78,91],"feature":[79],"extraction":[80],"phase":[81],"our":[83,119,135],"model,":[84],"harness":[86],"CLIP":[87],"extract":[89],"distinctive":[90],"features.":[92],"subsequent":[95],"caption":[96,110],"generation":[97],"stage,":[98],"enlist":[100],"assistance":[102],"GPT-2":[104],"enhance":[106],"accuracy":[108],"generation.":[111],"During":[112],"training":[114],"phase,":[115],"meticulously":[117],"train":[118],"on":[121],"distinct":[123],"datasets,":[124],"MS-COCO":[125],"and":[126,143],"Flickr30k.":[127],"Subsequently,":[128],"rigorously":[130],"evaluate":[131],"performance":[133],"trained":[136],"across":[138],"three":[139,151],"domains:":[140],"MS-COCO,":[141],"Flickr30k,":[142],"Cross-Domain,":[144],"consistently":[145],"achieving":[146],"outstanding":[147],"results":[148],"all":[150],"scenarios.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-05T09:29:38.588285","created_date":"2025-10-10T00:00:00"}