{"id":"https://openalex.org/W4285600262","doi":"https://doi.org/10.24963/ijcai.2022/384","title":"GL-RG: Global-Local Representation Granularity for Video Captioning","display_name":"GL-RG: Global-Local Representation Granularity for Video Captioning","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285600262","doi":"https://doi.org/10.24963/ijcai.2022/384"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/384","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/384","pdf_url":"https://www.ijcai.org/proceedings/2022/0384.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2022/0384.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051997091","display_name":"Liqi Yan","orcid":"https://orcid.org/0000-0002-7077-4947"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]},{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Liqi Yan","raw_affiliation_strings":["Fudan University","Rochester Institute of Technology","Westlake University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Rochester Institute of Technology","institution_ids":["https://openalex.org/I155173764"]},{"raw_affiliation_string":"Westlake University","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101774659","display_name":"Qifan Wang","orcid":"https://orcid.org/0000-0002-7570-5756"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qifan Wang","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103027806","display_name":"Yiming Cui","orcid":"https://orcid.org/0000-0003-2423-8972"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiming Cui","raw_affiliation_strings":["University of Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051925942","display_name":"Fuli Feng","orcid":"https://orcid.org/0000-0002-5828-9842"},"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":"Fuli Feng","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"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/A5040062188","display_name":"Xiaojun Quan","orcid":"https://orcid.org/0000-0002-8385-1083"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Quan","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362465","display_name":"Xiangyu Zhang","orcid":"https://orcid.org/0000-0003-2138-4608"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangyu Zhang","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101979289","display_name":"Dongfang Liu","orcid":"https://orcid.org/0000-0001-6995-4775"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongfang Liu","raw_affiliation_strings":["Rochester Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology","institution_ids":["https://openalex.org/I155173764"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8079,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.96343612,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2769","last_page":"2775"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9868999719619751,"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/T10515","display_name":"Cancer-related molecular mechanisms research","score":0.9724000096321106,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9867908954620361},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8436681032180786},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.687146782875061},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.677372932434082},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6230946779251099},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6048502922058105},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5971975326538086},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5517350435256958},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.520248532295227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4993722438812256},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2710157632827759},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1885124146938324},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08486476540565491},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07801172137260437}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9867908954620361},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8436681032180786},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.687146782875061},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.677372932434082},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6230946779251099},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6048502922058105},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5971975326538086},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5517350435256958},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.520248532295227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4993722438812256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2710157632827759},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1885124146938324},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08486476540565491},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07801172137260437},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/384","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/384","pdf_url":"https://www.ijcai.org/proceedings/2022/0384.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/384","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/384","pdf_url":"https://www.ijcai.org/proceedings/2022/0384.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285600262.pdf","grobid_xml":"https://content.openalex.org/works/W4285600262.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2016589492","https://openalex.org/W2139501017","https://openalex.org/W2164290393","https://openalex.org/W2425121537","https://openalex.org/W2549139847","https://openalex.org/W2729046720","https://openalex.org/W2745519816","https://openalex.org/W2766520430","https://openalex.org/W2948358897","https://openalex.org/W2962681491","https://openalex.org/W2962990649","https://openalex.org/W2963084599","https://openalex.org/W2963177403","https://openalex.org/W2963524571","https://openalex.org/W2963971014","https://openalex.org/W2964345285","https://openalex.org/W2966200295","https://openalex.org/W2981750519","https://openalex.org/W2982515679","https://openalex.org/W2984862483","https://openalex.org/W2985144848","https://openalex.org/W2988753485","https://openalex.org/W3010071343","https://openalex.org/W3029267566","https://openalex.org/W3034221024","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W3174257385","https://openalex.org/W3176425931","https://openalex.org/W3176514808","https://openalex.org/W3176689360","https://openalex.org/W3181286780","https://openalex.org/W4299341000"],"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/W3161079477","https://openalex.org/W2349962886"],"abstract_inverted_index":{"Video":[0],"captioning":[1,45,129],"is":[2,153],"a":[3,48,53,60,91,102,149],"challenging":[4,135],"task":[5,46],"as":[6],"it":[7],"needs":[8],"to":[9,84,95,100,125],"accurately":[10],"transform":[11],"visual":[12,78],"understanding":[13],"into":[14],"natural":[15],"language":[16],"description.":[17],"To":[18],"date,":[19],"state-of-the-art":[20,146],"methods":[21,147],"inadequately":[22],"model":[23,119],"global-local":[24,93],"representation":[25],"across":[26,108],"video":[27,44,57,82,106],"frames":[28],"for":[29,36,56],"caption":[30],"generation,":[31],"leaving":[32],"plenty":[33],"of":[34,105],"room":[35],"improvement.":[37],"In":[38],"this":[39],"work,":[40],"we":[41,74,89,111],"approach":[42],"the":[43,70,134],"from":[47,80],"new":[49],"perspective":[50],"and":[51,137],"propose":[52],"GL-RG":[54,65],"framework":[55],"captioning,":[58],"namely":[59],"Global-Local":[61],"Representation":[62],"Granularity.":[63],"Our":[64],"demonstrates":[66],"three":[67],"advantages":[68],"over":[69],"prior":[71],"efforts:":[72],"1)":[73],"explicitly":[75],"exploit":[76],"extensive":[77],"representations":[79],"different":[81],"ranges":[83],"improve":[85],"linguistic":[86],"expression;":[87],"2)":[88],"devise":[90],"novel":[92],"encoder":[94],"produce":[96],"rich":[97],"semantic":[98],"vocabulary":[99],"obtain":[101],"descriptive":[103],"granularity":[104],"contents":[107],"frames;":[109],"3)":[110],"develop":[112],"an":[113,122,127],"incremental":[114,123],"training":[115],"strategy":[116],"which":[117],"organizes":[118],"learning":[120],"in":[121],"fashion":[124],"incur":[126],"optimal":[128],"behavior.":[130],"Experimental":[131],"results":[132],"on":[133],"MSR-VTT":[136],"MSVD":[138],"datasets":[139],"show":[140],"that":[141],"our":[142],"DL-RG":[143],"outperforms":[144],"recent":[145],"by":[148],"significant":[150],"margin.":[151],"Code":[152],"available":[154],"at":[155],"https://github.com/ylqi/GL-RG.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":27},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}