{"id":"https://openalex.org/W3167051144","doi":"https://doi.org/10.1145/3446792","title":"A Multi-instance Multi-label Dual Learning Approach for Video Captioning","display_name":"A Multi-instance Multi-label Dual Learning Approach for Video Captioning","publication_year":2021,"publication_date":"2021-06-14","ids":{"openalex":"https://openalex.org/W3167051144","doi":"https://doi.org/10.1145/3446792","mag":"3167051144"},"language":"en","primary_location":{"id":"doi:10.1145/3446792","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3446792","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/A5070396907","display_name":"Wanting Ji","orcid":"https://orcid.org/0000-0003-2406-3156"},"institutions":[{"id":"https://openalex.org/I51158804","display_name":"Massey University","ror":"https://ror.org/052czxv31","country_code":"NZ","type":"education","lineage":["https://openalex.org/I51158804"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Wanting Ji","raw_affiliation_strings":["School of Natural and Computational Sciences, Massey University, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Natural and Computational Sciences, Massey University, Auckland, New Zealand","institution_ids":["https://openalex.org/I51158804"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100694558","display_name":"Ruili Wang","orcid":"https://orcid.org/0000-0001-7117-2772"},"institutions":[{"id":"https://openalex.org/I51158804","display_name":"Massey University","ror":"https://ror.org/052czxv31","country_code":"NZ","type":"education","lineage":["https://openalex.org/I51158804"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Ruili Wang","raw_affiliation_strings":["School of Natural and Computational Sciences, Massey University, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Natural and Computational Sciences, Massey University, Auckland, New Zealand","institution_ids":["https://openalex.org/I51158804"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I51158804"],"apc_list":null,"apc_paid":null,"fwci":1.7901,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.87001278,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"17","issue":"2s","first_page":"1","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9988999962806702,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9988999962806702,"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":0.9987999796867371,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9984999895095825,"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":0.9727778434753418},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8644527196884155},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7404212951660156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.606942892074585},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5047672986984253},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.43960168957710266},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3883479833602905},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3770788908004761},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3469925820827484},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17488938570022583}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9727778434753418},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8644527196884155},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7404212951660156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.606942892074585},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5047672986984253},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.43960168957710266},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3883479833602905},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3770788908004761},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3469925820827484},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17488938570022583},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3446792","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3446792","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1586939924","https://openalex.org/W1601567445","https://openalex.org/W1996430422","https://openalex.org/W2101105183","https://openalex.org/W2110119381","https://openalex.org/W2110933980","https://openalex.org/W2139501017","https://openalex.org/W2168901348","https://openalex.org/W2526417872","https://openalex.org/W2526468814","https://openalex.org/W2554906389","https://openalex.org/W2767577934","https://openalex.org/W2883112830","https://openalex.org/W2892181857","https://openalex.org/W2909821048","https://openalex.org/W2912238929","https://openalex.org/W2914095411","https://openalex.org/W2948905445","https://openalex.org/W2953461088","https://openalex.org/W2969136062","https://openalex.org/W2991618422","https://openalex.org/W3015304398","https://openalex.org/W3022162718","https://openalex.org/W3082436432","https://openalex.org/W3100255860","https://openalex.org/W4236965008"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Video":[0],"captioning":[1,26],"is":[2],"a":[3,45,69,102,111,120,202],"challenging":[4],"task":[5],"in":[6,34,58],"the":[7,56,83,134,146,149,158,163,166,169,177,184,189,192,195,210],"field":[8],"of":[9,148,212],"multimedia":[10],"processing,":[11],"which":[12,54],"aims":[13],"to":[14,20,40,77,118,129,141,162],"generate":[15,41,78,130],"informative":[16],"natural":[17],"language":[18],"descriptions/captions":[19],"describe":[21],"video":[22,25,42,52,79,94,124,131,135,213],"contents.":[23],"Previous":[24],"approaches":[27],"mainly":[28],"focused":[29],"on":[30,64,82,201],"capturing":[31],"visual":[32,139,197],"information":[33,57],"videos":[35,60,144,182],"using":[36,145],"an":[37],"encoder-decoder":[38],"structure":[39,48],"captions.":[43,62,132],"Recently,":[44],"new":[46],"encoder-decoder-reconstructor":[47,84],"was":[49],"proposed":[50],"for":[51],"captioning,":[53],"captured":[55],"both":[59],"and":[61,93,126,168,183,194],"Based":[63],"this,":[65],"this":[66],"article":[67],"proposes":[68],"novel":[70],"multi-instance":[71,114],"multi-label":[72,115],"dual":[73,154],"learning":[74,116,155],"approach":[75,174],"(MIMLDL)":[76],"captions":[80,186],"based":[81],"structure.":[85],"Specifically,":[86],"MIMLDL":[87,207],"contains":[88],"two":[89,159],"modules:":[90],"caption":[91,98,150],"generation":[92,99,151],"reconstruction":[95,136],"modules.":[96],"The":[97],"module":[100,137],"utilizes":[101],"lexical":[103,127],"fully":[104],"convolutional":[105],"neural":[106],"network":[107],"(Lexical":[108],"FCN)":[109],"with":[110],"weakly":[112],"supervised":[113],"mechanism":[117,156],"learn":[119],"translatable":[121],"mapping":[122],"between":[123,165,180,191],"regions":[125],"labels":[128],"Then":[133],"synthesizes":[138],"sequences":[140],"reproduce":[142],"raw":[143,167,181,196],"outputs":[147],"module.":[152],"A":[153],"fine-tunes":[157],"modules":[160],"according":[161],"gap":[164,179],"reproduced":[170,193],"videos.":[171],"Thus,":[172],"our":[173],"can":[175,208],"minimize":[176],"semantic":[178],"generated":[185],"by":[187],"minimizing":[188],"differences":[190],"sequences.":[198],"Experimental":[199],"results":[200],"benchmark":[203],"dataset":[204],"demonstrate":[205],"that":[206],"improve":[209],"accuracy":[211],"captioning.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}