{"id":"https://openalex.org/W4313476584","doi":"https://doi.org/10.1145/3576927","title":"NumCap: A Number-controlled Multi-caption Image Captioning Network","display_name":"NumCap: A Number-controlled Multi-caption Image Captioning Network","publication_year":2022,"publication_date":"2022-12-16","ids":{"openalex":"https://openalex.org/W4313476584","doi":"https://doi.org/10.1145/3576927"},"language":"en","primary_location":{"id":"doi:10.1145/3576927","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3576927","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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/A5057083285","display_name":"Amr Abdussalam","orcid":"https://orcid.org/0000-0001-9426-3415"},"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":"Amr Abdussalam","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-9426-3415","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/A5065761465","display_name":"Zhongfu Ye","orcid":"https://orcid.org/0000-0002-3207-2258"},"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":"Zhongfu Ye","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3207-2258","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/A5089032960","display_name":"Ammar Hawbani","orcid":"https://orcid.org/0000-0002-1069-3993"},"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":"Ammar Hawbani","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-1069-3993","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/A5067972997","display_name":"Majjed Al-Qatf","orcid":null},"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":"Majjed Al-Qatf","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-1796-344X","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/A5078898508","display_name":"Rashid Khan","orcid":"https://orcid.org/0000-0002-2410-044X"},"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":"Rashid Khan","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-2410-044X","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.8597,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.87111609,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"19","issue":"4","first_page":"1","last_page":"24"},"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":0.9962000250816345,"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":0.9876999855041504,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9544470310211182},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.802230715751648},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7582764625549316},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5776659250259399},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.551079273223877},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4674832224845886},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3331463634967804}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9544470310211182},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.802230715751648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7582764625549316},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5776659250259399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.551079273223877},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4674832224845886},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3331463634967804},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3576927","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3576927","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1970007001","https://openalex.org/W2053565832","https://openalex.org/W2061571889","https://openalex.org/W2069303182","https://openalex.org/W2185175083","https://openalex.org/W2302086703","https://openalex.org/W2336668576","https://openalex.org/W2531563875","https://openalex.org/W2560920409","https://openalex.org/W2745461083","https://openalex.org/W2754689878","https://openalex.org/W2764242590","https://openalex.org/W2801271919","https://openalex.org/W2884326683","https://openalex.org/W2906758315","https://openalex.org/W2908056713","https://openalex.org/W2909624347","https://openalex.org/W2922706279","https://openalex.org/W2943885184","https://openalex.org/W2945563815","https://openalex.org/W2951193251","https://openalex.org/W2962529143","https://openalex.org/W2962861647","https://openalex.org/W2962938439","https://openalex.org/W2962968835","https://openalex.org/W2965922392","https://openalex.org/W2974212192","https://openalex.org/W2985626746","https://openalex.org/W2987327987","https://openalex.org/W2990349092","https://openalex.org/W3003478339","https://openalex.org/W3009270862","https://openalex.org/W3035284526","https://openalex.org/W3036848992","https://openalex.org/W3038593179","https://openalex.org/W3039115681","https://openalex.org/W3045147787","https://openalex.org/W3082436432","https://openalex.org/W3093222659","https://openalex.org/W3093225449","https://openalex.org/W3094673569","https://openalex.org/W3098092829","https://openalex.org/W3110761028","https://openalex.org/W3112404983","https://openalex.org/W3125154076","https://openalex.org/W3136792391","https://openalex.org/W3148223059","https://openalex.org/W3154362247","https://openalex.org/W3162954998","https://openalex.org/W3193319282","https://openalex.org/W3211865849","https://openalex.org/W4213031069","https://openalex.org/W4226156236","https://openalex.org/W4287448984","https://openalex.org/W4293731196"],"related_works":["https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W3217388757","https://openalex.org/W1938708284","https://openalex.org/W4380190185","https://openalex.org/W3161816943","https://openalex.org/W2312145515"],"abstract_inverted_index":{"Image":[0],"captioning":[1,16,73],"is":[2,45,84,124,153,198],"a":[3,58,69,122,156,201],"promising":[4],"task":[5],"that":[6,75,195],"attracted":[7],"researchers":[8],"in":[9,187],"the":[10,62,115,127,140,146,150,161,165,168],"last":[11],"few":[12],"years.":[13],"Existing":[14],"image":[15,29,49,72,78,83,117,128],"models":[17,205],"are":[18,143],"primarily":[19],"trained":[20],"to":[21,46,96,99,126,130,155,159,210],"generate":[22,160],"one":[23,35],"caption":[24,36,55,98,142],"per":[25],"image.":[26,63],"However,":[27],"an":[28,48,77,93,104,132],"may":[30],"contain":[31],"rich":[32],"contents,":[33],"and":[34,139,179,206],"cannot":[37],"express":[38],"its":[39,101,208],"full":[40],"details.":[41],"A":[42],"better":[43],"solution":[44],"describe":[47],"with":[50,53,79,86,200],"multiple":[51,80,87],"captions,":[52],"each":[54,97],"focusing":[56],"on":[57,189],"specific":[59],"aspect":[60],"of":[61,167,203],"In":[64],"this":[65,137],"regard,":[66],"we":[67,91,109,172],"introduce":[68],"new":[70],"number-based":[71],"model":[74,158,184],"describes":[76],"sentences.":[81],"An":[82],"annotated":[85],"ground-truth":[88],"captions;":[89],"thus,":[90],"assign":[92],"external":[94],"number":[95,123],"distinguish":[100],"order.":[102],"Given":[103],"image-number":[105,133],"pair":[106],"as":[107],"input,":[108],"could":[110],"achieve":[111],"different":[112,119,212,215],"captions":[113],"for":[114],"same":[116],"under":[118,214],"numbers.":[120,217],"First,":[121],"attached":[125],"features":[129],"form":[131],"vector":[134,138],"(INV).":[135],"Then,":[136],"corresponding":[141],"embedded":[144],"using":[145,176],"order-embedding":[147],"approach.":[148],"Afterward,":[149],"INV\u2019s":[151],"embedding":[152],"fed":[154],"language":[157],"caption.":[162],"To":[163],"show":[164],"efficiency":[166],"numbers":[169],"incorporation":[170],"strategy,":[171],"conduct":[173],"extensive":[174],"experiments":[175],"MS-COCO,":[177],"Flickr30K,":[178],"Flickr8K":[180],"datasets.":[181],"The":[182,191],"proposed":[183],"attains":[185],"24.1":[186],"METEOR":[188],"MS-COCO.":[190],"achieved":[192],"results":[193],"demonstrate":[194],"our":[196],"method":[197],"competitive":[199],"range":[202],"state-of-the-art":[204],"validate":[207],"ability":[209],"produce":[211],"descriptions":[213],"given":[216]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":10}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
