{"id":"https://openalex.org/W4378768581","doi":"https://doi.org/10.48550/arxiv.2305.17784","title":"ConvGenVisMo: Evaluation of Conversational Generative Vision Models","display_name":"ConvGenVisMo: Evaluation of Conversational Generative Vision Models","publication_year":2023,"publication_date":"2023-05-28","ids":{"openalex":"https://openalex.org/W4378768581","doi":"https://doi.org/10.48550/arxiv.2305.17784"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2305.17784","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.17784","pdf_url":"https://arxiv.org/pdf/2305.17784","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":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.17784","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084161457","display_name":"Narjes Nikzad-Khasmakhi","orcid":"https://orcid.org/0000-0003-3536-1343","observed_orcids":["https://orcid.org/0000-0003-3536-1343"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khasmakhi, Narjes Nikzad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082152327","display_name":"Meysam Asgari-Chenaghlu","orcid":"https://orcid.org/0000-0002-7892-9675","observed_orcids":["https://orcid.org/0000-0002-7892-9675"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Asgari-Chenaghlu, Meysam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059577211","display_name":"Nabiha Asghar","orcid":"https://orcid.org/0000-0002-2034-5976","observed_orcids":["https://orcid.org/0000-0002-2034-5976"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Asghar, Nabiha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087564658","display_name":"Philipp Schaer","orcid":"https://orcid.org/0000-0002-8817-4632","observed_orcids":["https://orcid.org/0000-0002-8817-4632"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schaer, Philipp","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010708932","display_name":"Dietlind Z\u00fchlke","orcid":"https://orcid.org/0000-0003-3751-5887","observed_orcids":["https://orcid.org/0000-0003-3751-5887"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Z\u00fchlke, Dietlind","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0012000000569969416,"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":9.999999747378752e-05,"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/assessment-framework","display_name":"evaluation framework","score":0.6549999713897705},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.8949999809265137},{"id":"https://openalex.org/keywords/automatic-evaluation-metrics","display_name":"automatic evaluation metrics","score":0.9340000152587891},{"id":"https://openalex.org/keywords/human-machine-interaction","display_name":"human-machine interaction","score":0.7860000133514404},{"id":"https://openalex.org/keywords/multimodal-language-models","display_name":"multimodal language models","score":0.5529999732971191},{"id":"https://openalex.org/keywords/visual-generation","display_name":"visual generation","score":0.35600000619888306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8605163097381592},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.750241756439209},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.7395894527435303},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6995615363121033},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6570498943328857},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5541660785675049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5340014696121216},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5336965322494507},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5130687952041626},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.504670262336731},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4426136910915375},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.42296892404556274},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.42185789346694946},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3325265049934387},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2332562804222107},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16775572299957275},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.06694385409355164},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2305.17784","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.17784","pdf_url":"https://arxiv.org/pdf/2305.17784","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2305.17784","doi":"https://doi.org/10.48550/arxiv.2305.17784","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.17784","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.17784","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.17784","pdf_url":"https://arxiv.org/pdf/2305.17784","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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4378768581.pdf","grobid_xml":"https://content.openalex.org/works/W4378768581.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W3129576130","https://openalex.org/W4312933868","https://openalex.org/W4322718191","https://openalex.org/W4323717348"],"related_works":["https://openalex.org/W7202178093","https://openalex.org/W4393399744","https://openalex.org/W4386081496","https://openalex.org/W4405468241","https://openalex.org/W4412945604","https://openalex.org/W4404340653","https://openalex.org/W4402670365","https://openalex.org/W7167900635","https://openalex.org/W7143357448","https://openalex.org/W6907684267"],"abstract_inverted_index":{"Conversational":[0],"generative":[1],"vision":[2,20],"models":[3,27],"(CGVMs)":[4],"like":[5],"Visual":[6],"ChatGPT":[7],"(Wu":[8],"et":[9],"al.,":[10],"2023)":[11],"have":[12],"recently":[13],"emerged":[14],"from":[15,44],"the":[16,61,92,122,128,131],"synthesis":[17],"of":[18,65,95,113],"computer":[19],"and":[21,31,36,46,63,108,115,130],"natural":[22,30,50],"language":[23,51],"processing":[24],"techniques.":[25],"These":[26],"enable":[28],"more":[29],"interactive":[32],"communication":[33],"between":[34],"humans":[35],"machines,":[37],"because":[38],"they":[39],"can":[40],"understand":[41],"verbal":[42],"inputs":[43],"users":[45],"generate":[47],"responses":[48],"in":[49],"along":[52],"with":[53],"visual":[54],"outputs.":[55,123],"To":[56],"make":[57],"informed":[58],"decisions":[59],"about":[60],"usage":[62],"deployment":[64],"these":[66],"models,":[67],"it":[68],"is":[69],"important":[70],"to":[71,120],"analyze":[72],"their":[73],"performance":[74],"through":[75],"a":[76,89,100,111],"suitable":[77],"evaluation":[78,103,118,132],"framework":[79,90],"on":[80,139],"realistic":[81],"datasets.":[82],"In":[83],"this":[84,106],"paper,":[85],"we":[86],"present":[87],"ConvGenVisMo,":[88],"for":[91,105],"novel":[93],"task":[94],"evaluating":[96],"CGVMs.":[97],"ConvGenVisMo":[98,125],"introduces":[99],"new":[101,116],"benchmark":[102],"dataset":[104,129],"task,":[107],"also":[109],"provides":[110],"suite":[112],"existing":[114],"automated":[117],"metrics":[119],"evaluate":[121],"All":[124],"assets,":[126],"including":[127],"code,":[133],"will":[134],"be":[135],"made":[136],"available":[137],"publicly":[138],"GitHub.":[140]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-05-31T00:00:00"}