{"id":"https://openalex.org/W2964596963","doi":"https://doi.org/10.24963/ijcai.2019/135","title":"Video Interactive Captioning with Human Prompts","display_name":"Video Interactive Captioning with Human Prompts","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2964596963","doi":"https://doi.org/10.24963/ijcai.2019/135","mag":"2964596963"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/135","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/135","pdf_url":"https://www.ijcai.org/proceedings/2019/0135.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth 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/2019/0135.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066818276","display_name":"Aming Wu","orcid":"https://orcid.org/0000-0001-8426-0392"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aming Wu","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031819155","display_name":"Yahong Han","orcid":"https://orcid.org/0000-0003-2768-1398"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yahong Han","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005421447","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-0512-880X"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["Baidu Research","School of Computer Science, University of Technology Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research","institution_ids":["https://openalex.org/I98301712"]},{"raw_affiliation_string":"School of Computer Science, University of Technology Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0915,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.33208502,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"961","last_page":"967"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9979000091552734,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9829027056694031},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8616045713424683},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7014288902282715},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6706309914588928},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6417346596717834},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4891367256641388},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48133906722068787},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.475053071975708},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.46913689374923706},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.465703547000885},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4304274320602417},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.36152058839797974},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32363182306289673},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19207552075386047},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11025944352149963}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9829027056694031},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8616045713424683},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7014288902282715},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6706309914588928},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6417346596717834},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4891367256641388},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48133906722068787},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.475053071975708},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.46913689374923706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.465703547000885},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4304274320602417},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.36152058839797974},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32363182306289673},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19207552075386047},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11025944352149963},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2019/135","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/135","pdf_url":"https://www.ijcai.org/proceedings/2019/0135.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/139836","is_oa":false,"landing_page_url":"http://hdl.handle.net/10453/139836","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/135","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/135","pdf_url":"https://www.ijcai.org/proceedings/2019/0135.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G4407339161","display_name":null,"funder_award_id":"61876130","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G565454518","display_name":null,"funder_award_id":"U1509206,","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320318547","display_name":"Baidu","ror":"https://ror.org/03vs3wt56"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964596963.pdf","grobid_xml":"https://content.openalex.org/works/W2964596963.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W60493759","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2139501017","https://openalex.org/W2157331557","https://openalex.org/W2425121537","https://openalex.org/W2430148947","https://openalex.org/W2556388456","https://openalex.org/W2613904329","https://openalex.org/W2740388348","https://openalex.org/W2777622844","https://openalex.org/W2808647806","https://openalex.org/W2949298458","https://openalex.org/W2950553082","https://openalex.org/W2953318193","https://openalex.org/W2963177403","https://openalex.org/W2963840672","https://openalex.org/W2963843052","https://openalex.org/W2963971014","https://openalex.org/W2968831808","https://openalex.org/W3098682680","https://openalex.org/W4289547814","https://openalex.org/W4294149591","https://openalex.org/W4297909472","https://openalex.org/W4299341000"],"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/W4289422896"],"abstract_inverted_index":{"Video":[0],"captioning":[1,64,110],"aims":[2],"at":[3],"generating":[4,67],"a":[5,14,49,55,60,63,75,82,96,104,113,129,137,150,157],"proper":[6],"sentence":[7,35],"to":[8,38],"describe":[9],"the":[10,33,40,71,79,90,92,123,144,165,172,182,193,197],"video":[11,15,108,114,130],"content.":[12],"As":[13],"often":[16],"includes":[17],"rich":[18],"visual":[19],"content":[20],"and":[21,62,115,136],"semantic":[22],"details,":[23],"different":[24,30],"people":[25],"may":[26],"be":[27,147],"interested":[28],"in":[29],"views.":[31],"Thus":[32],"generated":[34],"always":[36],"fails":[37],"meet":[39],"ad":[41],"hoc":[42],"expectations.":[43],"In":[44],"this":[45,102],"paper,":[46],"we":[47,53,121,169],"make":[48],"new":[50,105],"attempt":[51],"that,":[52],"launch":[54],"round":[56],"of":[57,84,107,128,167,196],"interaction":[58,175],"between":[59],"human":[61,80],"agent.":[65],"After":[66],"an":[68,116,132],"initial":[69,117,133],"caption,":[70],"agent":[72,93,125],"asks":[73],"for":[74],"short":[76],"prompt":[77],"from":[78],"as":[81,119],"clue":[83],"his":[85],"expectation.":[86],"Then,":[87],"based":[88],"on":[89],"prompt,":[91],"could":[94],"generate":[95,186],"more":[97,187],"accurate":[98,188],"caption.":[99],"We":[100,141],"name":[101],"process":[103],"task":[106],"interactive":[109],"(ViCap).":[111],"Taking":[112],"caption":[118,134,139],"input,":[120],"devise":[122],"ViCap":[124,145],"which":[126],"consists":[127],"encoder,":[131,135],"refined":[138],"generator.":[140],"show":[142,181],"that":[143],"can":[146,184],"trained":[148],"via":[149],"full":[151],"supervision":[152,159],"(with":[153,160],"ground-truth)":[154],"way":[155],"or":[156],"weak":[158],"only":[161,180],"prompts)":[162],"way.":[163],"For":[164],"evaluation":[166],"ViCap,":[168],"first":[170],"extend":[171],"MSRVTT":[173],"with":[174],"ground-truth.":[176],"Experimental":[177],"results":[178],"not":[179],"prompts":[183],"help":[185],"captions,":[189],"but":[190],"also":[191],"demonstrate":[192],"good":[194],"performance":[195],"proposed":[198],"method.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}