{"id":"https://openalex.org/W3200409912","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534326","title":"VisDG: Towards Spontaneous Visual Dialogue Generation","display_name":"VisDG: Towards Spontaneous Visual Dialogue Generation","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3200409912","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534326","mag":"3200409912"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9534326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5040203410","display_name":"Qichuan Yang","orcid":"https://orcid.org/0000-0002-1689-5246"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qichuan Yang","raw_affiliation_strings":["Smart Education Lab, Research and Development of Lenovo, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Smart Education Lab, Research and Development of Lenovo, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103225546","display_name":"Liuxin Zhang","orcid":"https://orcid.org/0000-0002-6779-4920"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liuxin Zhang","raw_affiliation_strings":["Smart Education Lab, Research and Development of Lenovo, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Smart Education Lab, Research and Development of Lenovo, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049524014","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0003-0572-705X"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["Smart Education Lab, Research and Development of Lenovo, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Smart Education Lab, Research and Development of Lenovo, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072882523","display_name":"Jinghua Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinghua Gao","raw_affiliation_strings":["Smart Education Lab, Research and Development of Lenovo, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Smart Education Lab, Research and Development of Lenovo, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040203410"],"corresponding_institution_ids":["https://openalex.org/I4210156165"],"apc_list":null,"apc_paid":null,"fwci":0.0961,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39684641,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"1","last_page":"8"},"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":0.9944999814033508,"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":0.9889000058174133,"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/computer-science","display_name":"Computer science","score":0.8479173183441162},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.7666290998458862},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7338033318519592},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6819303631782532},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6388535499572754},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6008026599884033},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5808489918708801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5787030458450317},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5533087253570557},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.52434903383255},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5201430916786194},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5036346316337585},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4762956202030182},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3272096514701843},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.12650412321090698},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12094190716743469},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0805898904800415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8479173183441162},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.7666290998458862},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7338033318519592},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6819303631782532},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6388535499572754},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6008026599884033},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5808489918708801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5787030458450317},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5533087253570557},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.52434903383255},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5201430916786194},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5036346316337585},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4762956202030182},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3272096514701843},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.12650412321090698},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12094190716743469},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0805898904800415},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9534326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.49000000953674316,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1525961042","https://openalex.org/W1533861849","https://openalex.org/W1686810756","https://openalex.org/W1811254738","https://openalex.org/W1849277567","https://openalex.org/W1889081078","https://openalex.org/W1933349210","https://openalex.org/W1947481528","https://openalex.org/W2016053056","https://openalex.org/W2064675550","https://openalex.org/W2090243146","https://openalex.org/W2116435618","https://openalex.org/W2130942839","https://openalex.org/W2131726681","https://openalex.org/W2164290393","https://openalex.org/W2171361956","https://openalex.org/W2425121537","https://openalex.org/W2560920409","https://openalex.org/W2561715562","https://openalex.org/W2606982687","https://openalex.org/W2608109911","https://openalex.org/W2612619490","https://openalex.org/W2613904329","https://openalex.org/W2735308688","https://openalex.org/W2755728112","https://openalex.org/W2768661419","https://openalex.org/W2788148803","https://openalex.org/W2888779557","https://openalex.org/W2889844776","https://openalex.org/W2896348597","https://openalex.org/W2905571389","https://openalex.org/W2914699769","https://openalex.org/W2947169932","https://openalex.org/W2951390634","https://openalex.org/W2962684798","https://openalex.org/W2962706528","https://openalex.org/W2962749469","https://openalex.org/W2962806234","https://openalex.org/W2962883855","https://openalex.org/W2962910007","https://openalex.org/W2963188990","https://openalex.org/W2963351113","https://openalex.org/W2963403868","https://openalex.org/W2963420686","https://openalex.org/W2963442512","https://openalex.org/W2963622213","https://openalex.org/W2963623904","https://openalex.org/W2963890755","https://openalex.org/W2963954913","https://openalex.org/W2963991868","https://openalex.org/W2964265128","https://openalex.org/W2964345214","https://openalex.org/W2964352131","https://openalex.org/W2971373693","https://openalex.org/W2989322838","https://openalex.org/W2997035654","https://openalex.org/W2997547717","https://openalex.org/W4249013746","https://openalex.org/W4288252631","https://openalex.org/W4385245566","https://openalex.org/W6623987585","https://openalex.org/W6630875275","https://openalex.org/W6631399359","https://openalex.org/W6631943919","https://openalex.org/W6637373629","https://openalex.org/W6638742206","https://openalex.org/W6639204139","https://openalex.org/W6639432524","https://openalex.org/W6677326919","https://openalex.org/W6679492327","https://openalex.org/W6684090549","https://openalex.org/W6685230081","https://openalex.org/W6737602659","https://openalex.org/W6743477263","https://openalex.org/W6743731764","https://openalex.org/W6744137412","https://openalex.org/W6744852449","https://openalex.org/W6748878951","https://openalex.org/W6767651371"],"related_works":["https://openalex.org/W4236658683","https://openalex.org/W2020463334","https://openalex.org/W3157284875","https://openalex.org/W2026182709","https://openalex.org/W2259406085","https://openalex.org/W2099715052","https://openalex.org/W2147241511","https://openalex.org/W4226247999","https://openalex.org/W4213176082","https://openalex.org/W2187398150"],"abstract_inverted_index":{"Current":[0],"vision":[1],"and":[2,16,83,96,121,138],"language":[3],"understanding":[4],"tasks":[5],"can":[6],"be":[7],"generally":[8],"divided":[9],"into":[10],"two":[11],"categories:":[12],"image":[13,42,158],"(video)":[14],"description":[15,33],"visual":[17,95,113],"question":[18],"answering.":[19],"Both":[20],"of":[21,46,56,164],"them":[22],"aim":[23],"to":[24,79,146],"train":[25],"a":[26,32,44,49,53,81,89,105,111,135,149,156],"model":[27],"that":[28],"either":[29],"straightforwardly":[30],"generates":[31],"or":[34,43],"answers":[35],"the":[36,143,161,165,179,187],"predefined":[37],"questions":[38],"based":[39,92,118],"on":[40,93,119,186],"an":[41,76,128,172],"sequence":[45],"images":[47],"from":[48,125],"spectators":[50],"perspective.":[51],"However,":[52],"large":[54],"proportion":[55],"real-world":[57],"human":[58],"interactions":[59],"also":[60,170],"involve":[61],"spontaneous":[62,106],"dialogue":[63,114,141,166],"exchanges":[64],"among":[65],"multiple":[66],"speakers":[67],"as":[68,70,153,155],"well":[69,154],"dynamic":[71],"visual-textual":[72],"context,":[73],"which":[74,181],"requires":[75],"AI":[77],"agent":[78,144],"hold":[80],"natural":[82],"open-ended":[84],"dialog":[85],"with":[86],"humans":[87],"in":[88],"first-person":[90],"manner":[91],"both":[94,148],"textual":[97,151],"context.":[98],"To":[99],"move":[100],"closer":[101],"towards":[102],"achieving":[103],"such":[104],"multimodal":[107],"conversation,":[108],"we":[109,169],"introduce":[110],"new":[112],"generation":[115],"dataset":[116],"(VisDG)":[117],"keyframes":[120],"corresponding":[122,140],"subtitles":[123],"extracted":[124],"Friends":[126],"-":[127],"American":[129],"sitcom":[130],"television":[131],"series.":[132],"Specifically,":[133],"given":[134],"start":[136],"frame":[137],"its":[139],"text,":[142],"has":[145],"generate":[147],"meaningful":[150],"response":[152],"correct":[157],"candidate":[159],"for":[160,178],"latter":[162],"part":[163],"turn.":[167],"Furthermore,":[168],"propose":[171],"end-to-end":[173],"image-text":[174],"synergistic":[175],"network":[176],"(ITSN)":[177],"task,":[180],"outperforms":[182],"several":[183],"sophisticated":[184],"baselines":[185],"proposed":[188],"VisDG.":[189]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}