{"id":"https://openalex.org/W4362710615","doi":"https://doi.org/10.1145/3582649.3582658","title":"CITE: Compact Interactive TransformEr for Multilingual Image Captioning","display_name":"CITE: Compact Interactive TransformEr for Multilingual Image Captioning","publication_year":2023,"publication_date":"2023-01-06","ids":{"openalex":"https://openalex.org/W4362710615","doi":"https://doi.org/10.1145/3582649.3582658"},"language":"en","primary_location":{"id":"doi:10.1145/3582649.3582658","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3582649.3582658","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 6th International Conference on Image and Graphics Processing","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/A5022847062","display_name":"Yueyuan Xu","orcid":"https://orcid.org/0000-0002-9013-746X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yueyuan Xu","raw_affiliation_strings":["Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040235604","display_name":"Zhenzhen Hu","orcid":"https://orcid.org/0000-0003-1042-8361"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenzhen Hu","raw_affiliation_strings":["Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025436570","display_name":"Yuanen Zhou","orcid":"https://orcid.org/0000-0002-4986-3611"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanen Zhou","raw_affiliation_strings":["Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082236264","display_name":"Shijie Hao","orcid":"https://orcid.org/0000-0003-3181-1220"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shijie Hao","raw_affiliation_strings":["Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051332325","display_name":"Richang Hong","orcid":"https://orcid.org/0000-0001-5461-3986"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Richang Hong","raw_affiliation_strings":["Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5022847062"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.2407,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.49174861,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"34","issue":null,"first_page":"175","last_page":"181"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9754999876022339,"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":0.9940378069877625},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.803982138633728},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7780575156211853},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6446732878684998},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5050972104072571},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.49508801102638245},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47528162598609924},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45099544525146484},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3961758613586426},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06841841340065002},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06091177463531494}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9940378069877625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.803982138633728},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7780575156211853},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6446732878684998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5050972104072571},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.49508801102638245},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47528162598609924},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45099544525146484},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3961758613586426},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06841841340065002},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06091177463531494},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3582649.3582658","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3582649.3582658","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 6th International Conference on Image and Graphics Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W2781119031","https://openalex.org/W2913550731","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963527096","https://openalex.org/W2981994675","https://openalex.org/W2986670728","https://openalex.org/W3034655362","https://openalex.org/W3157860878","https://openalex.org/W3173220247","https://openalex.org/W3205071568","https://openalex.org/W4239019441","https://openalex.org/W4241499611","https://openalex.org/W4365800005"],"related_works":["https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W4323777661","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W3049463507","https://openalex.org/W2936497627","https://openalex.org/W4288365749","https://openalex.org/W3013624417"],"abstract_inverted_index":{"Current":[0],"state-of-the-art":[1],"image":[2,23,42,64,149],"captioning":[3,24,43,71,187],"models":[4,18],"generate":[5],"captions":[6,150],"in":[7,65,95],"a":[8,12,21,53,114,158],"single":[9,54,170],"language,":[10],"requiring":[11],"combination":[13],"of":[14,30,39,127,135,151],"multiple":[15,66],"language":[16],"specific":[17],"to":[19,36,113,117,123],"build":[20],"multilingual":[22,41,115],"system.":[25],"However,":[26],"as":[27],"the":[28,37,40,70,78,84,92,96,99,107,124,133,148,152,164,178,185],"number":[29],"supported":[31],"languages":[32,67],"increases,":[33],"it":[34],"leads":[35],"parameters":[38,89],"system":[44,72],"grow":[45],"linearly.":[46],"To":[47],"tackle":[48],"this":[49],"issue,":[50],"we":[51,82,105,131],"propose":[52],"Compact":[55],"Interactive":[56],"TransformEr":[57],"(CITE)":[58],"model,":[59,81],"which":[60],"can":[61,176],"describe":[62],"an":[63],"simultaneously,":[68],"making":[69],"more":[73,174],"compact.":[74],"Specifically,":[75],"based":[76],"on":[77,163],"standard":[79],"Transformer":[80],"share":[83],"encoder":[85],"and":[86,90,129,143,156],"decoder":[87,97],"backbone":[88],"replace":[91],"self-attention":[93],"sub-layer":[94],"with":[98,173],"interactive":[100],"attention":[101],"sub-layer.":[102],"In":[103],"addition,":[104],"extend":[106],"traditional":[108],"monolingual":[109,186],"reinforcement":[110],"learning":[111],"mechanism":[112],"version":[116],"promote":[118],"better":[119,183],"description":[120],"generation.":[121],"Due":[122],"wide":[125],"use":[126],"Chinese":[128,144],"English,":[130],"evaluate":[132],"performance":[134,180],"our":[136,169],"CITE":[137,171],"model":[138,172],"by":[139],"simultaneously":[140],"generating":[141],"English":[142],"captions.":[145],"We":[146],"expand":[147],"whole":[153],"MSCOCO":[154],"dataset":[155,166],"release":[157],"COCO-EN-CN":[159,165],"dataset.":[160],"Extensive":[161],"experiments":[162],"show":[167],"that":[168],"parameter-efficient":[175],"maintain":[177],"competitive":[179],"or":[181],"even":[182],"than":[184],"models.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}