{"id":"https://openalex.org/W4249013746","doi":"https://doi.org/10.1109/cvpr.2017.121","title":"Visual Dialog","display_name":"Visual Dialog","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W4249013746","doi":"https://doi.org/10.1109/cvpr.2017.121","mag":"3037108562"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2017.121","doi":"https://doi.org/10.1109/cvpr.2017.121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2017.121","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1611.08669v5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102972112","display_name":"Abhishek Das","orcid":"https://orcid.org/0000-0002-4718-4316","observed_orcids":["https://orcid.org/0000-0002-4718-4316"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhishek Das","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070914582","display_name":"Satwik Kottur","orcid":"https://orcid.org/0000-0003-0207-8680","observed_orcids":["https://orcid.org/0000-0003-0207-8680"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Satwik Kottur","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055812247","display_name":"Khushi Gupta","orcid":"https://orcid.org/0000-0002-4452-5103","observed_orcids":["https://orcid.org/0000-0002-4452-5103"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khushi Gupta","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071640510","display_name":"Avi Singh","orcid":"https://orcid.org/0009-0002-7874-6999","observed_orcids":["https://orcid.org/0009-0002-7874-6999"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Avi Singh","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Deshraj Yadav","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deshraj Yadav","raw_affiliation_strings":["Virginia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045861415","display_name":"Jos\u00e9 M. F. Moura","orcid":"https://orcid.org/0000-0002-9822-8294","observed_orcids":["https://orcid.org/0000-0002-9822-8294"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jose M. F. Moura","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050342343","display_name":"Devi Parikh","orcid":"https://orcid.org/0000-0002-3779-6706","observed_orcids":["https://orcid.org/0000-0002-3779-6706"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Devi Parikh","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014035752","display_name":"Dhruv Batra","orcid":"https://orcid.org/0000-0002-1358-0011","observed_orcids":["https://orcid.org/0000-0002-1358-0011"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhruv Batra","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.5187,"has_fulltext":false,"cited_by_count":479,"citation_normalized_percentile":{"value":0.98683185,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1080","last_page":"1089"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9984999895095825,"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":0.9984999895095825,"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/T12031","display_name":"Speech and dialogue systems","score":0.0012000000569969416,"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"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":9.999999747378752e-05,"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/visual-dialogue","display_name":"visual dialogue","score":0.9309999942779541},{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"visual question answering","score":0.6159999966621399},{"id":"https://openalex.org/keywords/human-ai-dialogue","display_name":"human-AI dialogue","score":0.5379999876022339},{"id":"https://openalex.org/keywords/chatbots","display_name":"chatbots","score":0.460999995470047},{"id":"https://openalex.org/keywords/encoder-decoder-architecture","display_name":"encoder-decoder architecture","score":0.7689999938011169},{"id":"https://openalex.org/keywords/memory-networks","display_name":"memory networks","score":0.7879999876022339},{"id":"https://openalex.org/keywords/decision-level-fusion","display_name":"decision fusion","score":0.7979999780654907},{"id":"https://openalex.org/keywords/mean-reciprocal-rank","display_name":"mean reciprocal rank","score":0.6759999990463257}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.9102524518966675},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8077881336212158},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6261469125747681},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6043277382850647},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.5361760854721069},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5031740069389343},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.46279239654541016},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43969401717185974},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42658284306526184},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.389495313167572},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3206426501274109},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3004540503025055},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11579716205596924},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cvpr.2017.121","doi":"https://doi.org/10.1109/cvpr.2017.121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2017.121","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"mag:3037108562","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1611.08669v5","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3037108562","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1611.08669v5","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W580074167","https://openalex.org/W1525961042","https://openalex.org/W1544827683","https://openalex.org/W1575833922","https://openalex.org/W1591706642","https://openalex.org/W1686810756","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1895641373","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1933065844","https://openalex.org/W1933349210","https://openalex.org/W1947481528","https://openalex.org/W1983405110","https://openalex.org/W1983927101","https://openalex.org/W2047192163","https://openalex.org/W2048343491","https://openalex.org/W2058556535","https://openalex.org/W2078238240","https://openalex.org/W2125320996","https://openalex.org/W2136036867","https://openalex.org/W2139501017","https://openalex.org/W2142192571","https://openalex.org/W2145339207","https://openalex.org/W2151498684","https://openalex.org/W2175256910","https://openalex.org/W2189070436","https://openalex.org/W2190067570","https://openalex.org/W2194775991","https://openalex.org/W2202226326","https://openalex.org/W2247513039","https://openalex.org/W2257979135","https://openalex.org/W2302548814","https://openalex.org/W2304545146","https://openalex.org/W2373570000","https://openalex.org/W2403702038","https://openalex.org/W2407656382","https://openalex.org/W2424413254","https://openalex.org/W2463267937","https://openalex.org/W2463565445","https://openalex.org/W2471094925","https://openalex.org/W2471684853","https://openalex.org/W2472559481","https://openalex.org/W2527800741","https://openalex.org/W2558809543","https://openalex.org/W2560730294","https://openalex.org/W2583186419","https://openalex.org/W2951619830","https://openalex.org/W2952228917","https://openalex.org/W2962749469","https://openalex.org/W2962790689","https://openalex.org/W2962854379","https://openalex.org/W2962883855","https://openalex.org/W2963167310","https://openalex.org/W2963393863","https://openalex.org/W2963668159","https://openalex.org/W2963748441","https://openalex.org/W2963790827","https://openalex.org/W2963890019","https://openalex.org/W2963903950","https://openalex.org/W2963954913","https://openalex.org/W2964121744","https://openalex.org/W2964210218","https://openalex.org/W3022187094","https://openalex.org/W3087871082","https://openalex.org/W3106250896","https://openalex.org/W7072257459"],"related_works":["https://openalex.org/W6884715904","https://openalex.org/W2794519117","https://openalex.org/W4386381838","https://openalex.org/W4390136499","https://openalex.org/W2963791035","https://openalex.org/W7062842953","https://openalex.org/W2996781902","https://openalex.org/W3118856670","https://openalex.org/W7126215267","https://openalex.org/W7071631223"],"abstract_inverted_index":{"We":[0,94,132,167,199],"introduce":[1,133],"the":[2,37,39,44,54,121,177,208,233],"task":[3,66,211],"of":[4,75,88,127,136,164,186,196],"Visual":[5,57,106,141,174,209],"Dialog,":[6],"which":[7,160],"requires":[8],"an":[9,28],"AI":[10,178],"agent":[11,40,179],"to":[12,42,69,84,102,182],"hold":[13],"a":[14,30,34,63,72,96,104,125,134,162,169,184],"meaningful":[15],"dialog":[16,31,113,129],"with":[17,124,143],"humans":[18],"in":[19,46,81],"natural,":[20],"conversational":[21],"language":[22],"about":[23,36],"visual":[24,235],"content.":[25],"Specifically,":[26],"given":[27],"image,":[29,38,47],"history,":[32,51],"and":[33,52,91,151,154,158,189,204,218],"question":[35,45,55],"has":[41],"ground":[43],"infer":[48],"context":[49],"from":[50,62,120],"answer":[53],"accurately.":[56],"Dialog":[58,107,142,175,210],"is":[59,180],"disentangled":[60],"enough":[61,83],"specific":[64],"downstream":[65],"so":[67],"as":[68,71,194],"serve":[70],"general":[73],"test":[74],"machine":[76,203],"intelligence,":[77],"while":[78],"being":[79],"grounded":[80],"vision":[82],"allow":[85],"objective":[86],"evaluation":[87,171],"individual":[89],"responses":[90],"benchmark":[92],"progress.":[93],"develop":[95],"novel":[97],"two-person":[98],"chat":[99],"data-collection":[100],"protocol":[101,172],"curate":[103],"large-scale":[105],"dataset":[108],"(VisDial).":[109],"VisDial":[110],"contains":[111],"1":[112],"(10":[114],"question-answer":[115,130],"pairs)":[116],"on":[117,191,207],"~140k":[118],"images":[119],"COCO":[122],"dataset,":[123,216],"total":[126],"~1.4M":[128],"pairs.":[131],"family":[135],"neural":[137],"encoder-decoder":[138],"models":[139,220],"for":[140,173],"3":[144],"encoders":[145],"(Late":[146],"Fusion,":[147],"Hierarchical":[148],"Recurrent":[149],"Encoder":[150],"Memory":[152],"Network)":[153],"2":[155],"decoders":[156],"(generative":[157],"discriminative),":[159],"outperform":[161],"number":[163],"sophisticated":[165],"baselines.":[166],"propose":[168],"retrieval-based":[170],"where":[176],"asked":[181],"sort":[183],"set":[185],"candidate":[187],"answers":[188],"evaluated":[190],"metrics":[192],"such":[193],"mean-reciprocal-rank":[195],"human":[197,205,213],"response.":[198],"quantify":[200],"gap":[201],"between":[202],"performance":[206],"via":[212],"studies.":[214],"Our":[215],"code,":[217],"trained":[219],"will":[221],"be":[222],"released":[223],"publicly":[224],"at":[225],"https://visualdialog.org.":[226],"Putting":[227],"it":[228],"all":[229],"together,":[230],"we":[231],"demonstrate":[232],"first":[234],"chatbot!.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":22},{"year":2025,"cited_by_count":49},{"year":2024,"cited_by_count":51},{"year":2023,"cited_by_count":58},{"year":2022,"cited_by_count":69},{"year":2021,"cited_by_count":81},{"year":2020,"cited_by_count":55},{"year":2019,"cited_by_count":53},{"year":2018,"cited_by_count":31},{"year":2017,"cited_by_count":10}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2022-05-12T00:00:00"}