{"id":"https://openalex.org/W3035372819","doi":"https://doi.org/10.24963/ijcai.2020/104","title":"Learning to Discretely Compose Reasoning Module Networks for Video Captioning","display_name":"Learning to Discretely Compose Reasoning Module Networks for Video Captioning","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3035372819","doi":"https://doi.org/10.24963/ijcai.2020/104","mag":"3035372819"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/104","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/104","pdf_url":"https://www.ijcai.org/proceedings/2020/0104.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0104.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056587842","display_name":"Ganchao Tan","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":true,"raw_author_name":"Ganchao Tan","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101424059","display_name":"Daqing Liu","orcid":"https://orcid.org/0000-0002-8286-0105"},"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":"Daqing Liu","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377147","display_name":"Meng Wang","orcid":"https://orcid.org/0000-0002-3094-7735"},"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":"Meng Wang","raw_affiliation_strings":["Hefei University of Technology"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003217535","display_name":"Zheng-Jun Zha","orcid":"https://orcid.org/0000-0003-2510-8993"},"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":"Zheng-Jun Zha","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056587842"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":4.9073,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":{"value":0.96266702,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"745","last_page":"752"},"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":0.9952999949455261,"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":0.9804999828338623,"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":0.9460729360580444},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.818934977054596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6013347506523132},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5658261775970459},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5479419827461243},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5432982444763184},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4851883053779602},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.46027255058288574},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4131147861480713},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.27610287070274353},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2171006202697754}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9460729360580444},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.818934977054596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6013347506523132},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5658261775970459},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5479419827461243},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5432982444763184},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4851883053779602},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.46027255058288574},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4131147861480713},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27610287070274353},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2171006202697754},{"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:10.24963/ijcai.2020/104","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/104","pdf_url":"https://www.ijcai.org/proceedings/2020/0104.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/104","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/104","pdf_url":"https://www.ijcai.org/proceedings/2020/0104.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1794953508","display_name":null,"funder_award_id":"B13002","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2376276132","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2439238222","display_name":null,"funder_award_id":"B13002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3584809445","display_name":null,"funder_award_id":"U19B2038","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4530701113","display_name":null,"funder_award_id":"WK2100100030","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5232388117","display_name":null,"funder_award_id":"61725203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5279355306","display_name":null,"funder_award_id":"2100100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6197875348","display_name":null,"funder_award_id":"61620106009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7033253288","display_name":null,"funder_award_id":"Grants","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8951484681","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3035372819.pdf","grobid_xml":"https://content.openalex.org/works/W3035372819.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2123301721","https://openalex.org/W2133564696","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2154652894","https://openalex.org/W2164290393","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2547875792","https://openalex.org/W2556388456","https://openalex.org/W2619947201","https://openalex.org/W2740388348","https://openalex.org/W2745461083","https://openalex.org/W2788810331","https://openalex.org/W2883104598","https://openalex.org/W2887585070","https://openalex.org/W2905145027","https://openalex.org/W2938603906","https://openalex.org/W2946086442","https://openalex.org/W2948358897","https://openalex.org/W2962681491","https://openalex.org/W2962990649","https://openalex.org/W2963224792","https://openalex.org/W2963524571","https://openalex.org/W2964118342","https://openalex.org/W2964350391","https://openalex.org/W2964896648","https://openalex.org/W2984121207","https://openalex.org/W2984862483","https://openalex.org/W2988023442","https://openalex.org/W2988753485","https://openalex.org/W2990069284","https://openalex.org/W4299341000"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W3009270862"],"abstract_inverted_index":{"Generating":[0],"natural":[1],"language":[2],"descriptions":[3],"for":[4,59,69,101],"videos,":[5],"i.e.,":[6],"video":[7,67,102],"captioning,":[8,68,103],"essentially":[9],"requires":[10,71],"step-by-step":[11],"reasoning":[12,56,75,99,118,128],"along":[13,87],"the":[14,21,36,42,48,88,111,116,155,159],"generation":[15,89,168],"process.":[16,90,169],"For":[17],"example,":[18],"to":[19,31,66,109],"generate":[20],"sentence":[22],"\u201ca":[23],"man":[24,43],"is":[25,44,172],"shooting":[26],"a":[27,96,132,140,144],"basketball\u201d,":[28],"we":[29,94],"need":[30],"first":[32],"locate":[33],"and":[34,81,83,130,134,151,166],"describe":[35,47],"subject":[37],"\u201cman\u201d,":[38],"next":[39],"reason":[40],"out":[41],"\u201cshooting\u201d,":[45],"then":[46],"object":[49],"\u201cbasketball\u201d":[50],"of":[51],"shooting.":[52],"However,":[53],"existing":[54,112],"visual":[55,60,74,98],"methods":[57,161],"designed":[58],"question":[61],"answering":[62],"are":[63],"not":[64],"appropriate":[65],"it":[70],"more":[72],"complex":[73],"on":[76,149],"videos":[77],"over":[78],"both":[79],"space":[80],"time,":[82],"dynamic":[84,133],"module":[85,136],"composition":[86],"In":[91],"this":[92],"paper,":[93],"propose":[95],"novel":[97],"approach":[100],"named":[104],"Reasoning":[105],"Module":[106],"Networks":[107],"(RMN),":[108],"equip":[110],"encoder-decoder":[113],"framework":[114],"with":[115,143],"above":[117],"capacity.":[119],"Specifically,":[120],"our":[121],"RMN":[122,157],"employs":[123],"1)":[124],"three":[125],"sophisticated":[126],"spatio-temporal":[127],"modules,":[129],"2)":[131],"discrete":[135],"selector":[137],"trained":[138],"by":[139],"linguistic":[141],"loss":[142],"Gumbel":[145],"approximation.":[146],"Extensive":[147],"experiments":[148],"MSVD":[150],"MSR-VTT":[152],"datasets":[153],"demonstrate":[154],"proposed":[156],"outperforms":[158],"state-of-the-art":[160],"while":[162],"providing":[163],"an":[164],"explicit":[165],"explainable":[167],"Our":[170],"code":[171],"available":[173],"at":[174],"https://github.com/tgc1997/RMN.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}
