{"id":"https://openalex.org/W4385768107","doi":"https://doi.org/10.24963/ijcai.2023/180","title":"Prompt Learns Prompt: Exploring Knowledge-Aware Generative Prompt Collaboration For Video Captioning","display_name":"Prompt Learns Prompt: Exploring Knowledge-Aware Generative Prompt Collaboration For Video Captioning","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385768107","doi":"https://doi.org/10.24963/ijcai.2023/180"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/180","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/180","pdf_url":"https://www.ijcai.org/proceedings/2023/0180.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second 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/2023/0180.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/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqi Yan","raw_affiliation_strings":["Fudan University","Westlake Institute for Advanced Study, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Westlake Institute for Advanced Study, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100325126","display_name":"Cheng Han","orcid":"https://orcid.org/0000-0002-8145-3436"},"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":"Cheng Han","raw_affiliation_strings":["Rochester Institute of Technology","Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology","institution_ids":["https://openalex.org/I155173764"]},{"raw_affiliation_string":"Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051227924","display_name":"Zenglin Xu","orcid":"https://orcid.org/0000-0001-5550-6461"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zenglin Xu","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen","School of Computer Science and Technology, Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","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":true,"raw_author_name":"Dongfang Liu","raw_affiliation_strings":["Rochester Institute of Technology","Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology","institution_ids":["https://openalex.org/I155173764"]},{"raw_affiliation_string":"Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"last","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","Meta AI, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]},{"raw_affiliation_string":"Meta AI, Meta","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101979289"],"corresponding_institution_ids":["https://openalex.org/I155173764"],"apc_list":null,"apc_paid":null,"fwci":4.2484,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.95873267,"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":"1622","last_page":"1630"},"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":0.9962000250816345,"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":0.9944999814033508,"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":0.9647151231765747},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.867546796798706},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6639640927314758},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5571458339691162},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5150148868560791},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4579457640647888},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4516724944114685},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4473001956939697},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.444776713848114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4201710820198059},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3878073990345001},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10109373927116394}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9647151231765747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.867546796798706},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6639640927314758},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5571458339691162},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5150148868560791},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4579457640647888},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4516724944114685},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4473001956939697},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.444776713848114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4201710820198059},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3878073990345001},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10109373927116394},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/180","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/180","pdf_url":"https://www.ijcai.org/proceedings/2023/0180.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/180","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/180","pdf_url":"https://www.ijcai.org/proceedings/2023/0180.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385768107.pdf"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2108325777","https://openalex.org/W2123301721","https://openalex.org/W2139501017","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2896457183","https://openalex.org/W2948358897","https://openalex.org/W2962681491","https://openalex.org/W2963177403","https://openalex.org/W2963971014","https://openalex.org/W2984862483","https://openalex.org/W2993383518","https://openalex.org/W3015468748","https://openalex.org/W3034221024","https://openalex.org/W3034445277","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W3044438666","https://openalex.org/W3094502228","https://openalex.org/W3098267758","https://openalex.org/W3126721948","https://openalex.org/W3138516171","https://openalex.org/W3166396011","https://openalex.org/W3174770825","https://openalex.org/W3176425931","https://openalex.org/W3176514808","https://openalex.org/W3176689360","https://openalex.org/W3185341429","https://openalex.org/W3198377975","https://openalex.org/W4205991051","https://openalex.org/W4214612132","https://openalex.org/W4221167659","https://openalex.org/W4226065437","https://openalex.org/W4285118488","https://openalex.org/W4285600262","https://openalex.org/W4287704453","https://openalex.org/W4296151208","https://openalex.org/W4297795751","https://openalex.org/W4297847583","https://openalex.org/W4302012752","https://openalex.org/W4306313147","https://openalex.org/W4309864938","https://openalex.org/W4312310776","https://openalex.org/W4312457137","https://openalex.org/W4312480274","https://openalex.org/W4312560592","https://openalex.org/W4312747482","https://openalex.org/W4313186260","https://openalex.org/W4313194685","https://openalex.org/W4320712030","https://openalex.org/W4386071547","https://openalex.org/W4386076600"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4399485860"],"abstract_inverted_index":{"Fine-tuning":[0],"large":[1],"vision-language":[2],"models":[3],"is":[4],"a":[5,76,89,109],"challenging":[6],"task.":[7],"Prompt":[8,78,104,111],"tuning":[9,79],"approaches":[10],"have":[11],"been":[12],"introduced":[13],"to":[14,92,113,125],"learn":[15,40,54],"fixed":[16],"textual":[17],"or":[18],"visual":[19],"prompts":[20,39,49,56,66,120,148],"while":[21],"freezing":[22],"the":[23,30,51,58,115,118,123,132,146,153],"pre-trained":[24],"model":[25,91,124],"in":[26,50,67],"downstream":[27],"tasks.":[28],"Despite":[29],"effectiveness":[31],"of":[32,65,135],"prompt":[33],"tuning,":[34],"what":[35],"do":[36],"those":[37],"learnable":[38],"remains":[41],"unexplained.":[42],"In":[43],"this":[44],"work,":[45],"we":[46,74,107],"explore":[47],"whether":[48],"fine-tuning":[52,70],"can":[53],"knowledge-aware":[55,119,154],"from":[57,117,152],"pre-training,":[59],"by":[60],"designing":[61],"two":[62],"different":[63],"sets":[64],"pre-training":[68],"and":[69,98,121],"phases":[71],"respectively.":[72],"Specifically,":[73],"present":[75],"Video-Language":[77,110],"(VL-Prompt)":[80],"approach":[81,137],"for":[82],"video":[83],"captioning,":[84],"which":[85],"first":[86],"efficiently":[87],"pre-train":[88],"video-language":[90,147],"extract":[93],"key":[94],"information":[95],"(e.g.,":[96],"actions":[97],"objects)":[99],"with":[100],"flexibly":[101],"generated":[102],"Knowledge-Aware":[103],"(KAP).":[105],"Then,":[106],"design":[108],"(VLP)":[112],"transfer":[114],"knowledge":[116],"fine-tune":[122],"generate":[126],"full":[127],"captions.":[128],"Experimental":[129],"results":[130],"show":[131],"superior":[133],"performance":[134],"our":[136],"over":[138],"several":[139],"state-of-the-art":[140],"baselines.":[141],"We":[142],"further":[143],"demonstrate":[144],"that":[145],"are":[149],"well":[150],"learned":[151],"prompts.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}