{"id":"https://openalex.org/W4415797331","doi":"https://doi.org/10.52202/079017-2096","title":"VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models","display_name":"VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4415797331","doi":"https://doi.org/10.52202/079017-2096"},"language":"en","primary_location":{"id":"doi:10.52202/079017-2096","doi":"https://doi.org/10.52202/079017-2096","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-2096","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.06098","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100390307","display_name":"Wenhao Wang","orcid":"https://orcid.org/0000-0001-7566-2322","observed_orcids":["https://orcid.org/0000-0001-7566-2322","https://orcid.org/0000-0001-8727-1572","https://orcid.org/0000-0002-5779-9808"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenhao Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005421447","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-0512-880X","observed_orcids":["https://orcid.org/0000-0002-0512-880X","https://orcid.org/0000-0001-5528-0546","https://orcid.org/0000-0002-1330-9985"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Yang","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":10.7149,"has_fulltext":true,"cited_by_count":74,"citation_normalized_percentile":{"value":0.98783503,"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":"65618","last_page":"65642"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0,"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/text-to-video-diffusion-models","display_name":"text-to-video diffusion models","score":0.8289999961853027},{"id":"https://openalex.org/keywords/sora","display_name":"Sora","score":0.7450000047683716},{"id":"https://openalex.org/keywords/prompt-engineering","display_name":"prompt engineering","score":0.6759999990463257},{"id":"https://openalex.org/keywords/video-generation","display_name":"video generation","score":0.6890000104904175},{"id":"https://openalex.org/keywords/video-copy-detection","display_name":"video copy detection","score":0.7509999871253967},{"id":"https://openalex.org/keywords/data-curation","display_name":"data curation","score":0.6840000152587891}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41429999470710754},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3874000012874603},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3206000030040741},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3179999887943268},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29789999127388},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2637999951839447},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2540999948978424}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/079017-2096","doi":"https://doi.org/10.52202/079017-2096","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-2096","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2403.06098","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.06098","pdf_url":"https://arxiv.org/pdf/2403.06098","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2403.06098","doi":"https://doi.org/10.48550/arxiv.2403.06098","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.06098","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:2403.06098","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.06098","pdf_url":"https://arxiv.org/pdf/2403.06098","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415797331.pdf","grobid_xml":"https://content.openalex.org/works/W4415797331.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W3194309076","https://openalex.org/W3212628310","https://openalex.org/W4310428424","https://openalex.org/W4366734606","https://openalex.org/W4367000155","https://openalex.org/W4377864168","https://openalex.org/W4378499102","https://openalex.org/W4384392955","https://openalex.org/W4385571801","https://openalex.org/W4385848606","https://openalex.org/W4387994353","https://openalex.org/W4388844352","https://openalex.org/W4389115686","https://openalex.org/W4390137271","https://openalex.org/W4390872556","https://openalex.org/W4390897529","https://openalex.org/W4391009376","https://openalex.org/W4392904043","https://openalex.org/W4393924649","https://openalex.org/W4400949264","https://openalex.org/W4402387301","https://openalex.org/W4407881938","https://openalex.org/W4409014148","https://openalex.org/W4413157524"],"related_works":["https://openalex.org/W4404404779","https://openalex.org/W4400375159","https://openalex.org/W4403370734","https://openalex.org/W4415085809","https://openalex.org/W4405655761","https://openalex.org/W4307479129","https://openalex.org/W4396762397","https://openalex.org/W4413157704","https://openalex.org/W4396835080","https://openalex.org/W4318147046"],"abstract_inverted_index":{"The":[0,169],"arrival":[1],"of":[2,45,89],"Sora":[3],"marks":[4],"a":[5,43,93,107,123],"new":[6,108,140],"era":[7],"for":[8,106,113,127,158],"text-to-video":[9,26,46,114,148],"diffusion":[10,27,78,159],"models,":[11,28,79],"bringing":[12],"significant":[13],"advancements":[14],"in":[15],"video":[16,152,155],"generation":[17,115],"and":[18,34,99,132,154,166,176],"potential":[19],"applications.":[20],"However,":[21],"Sora,":[22],"along":[23],"with":[24],"other":[25],"is":[29,36,96,179],"highly":[30],"reliant":[31],"on":[32],"prompts,":[33],"there":[35],"no":[37],"publicly":[38,180],"available":[39,181],"dataset":[40,57,69,110,126,134,174],"that":[41,95],"features":[42],"study":[44],"prompts.":[47],"In":[48],"this":[49,68,90],"paper,":[50],"we":[51,102,145],"introduce":[52],"VidProM,":[53],"the":[54,87,104,172,185],"first":[55],"large-scale":[56,91,124],"comprising":[58],"1.67":[59],"Million":[60],"unique":[61],"text-to-Video":[62],"Prompts":[63],"from":[64,121],"real":[65],"users.":[66],"Additionally,":[67],"includes":[70],"6.69":[71],"million":[72],"videos":[73],"generated":[74],"by":[75,116],"four":[76],"state-of-the-art":[77],"alongside":[80],"some":[81],"related":[82,177],"data.":[83],"We":[84],"initially":[85],"discuss":[86],"curation":[88],"dataset,":[92],"process":[94],"both":[97],"time-consuming":[98],"costly.":[100],"Subsequently,":[101],"underscore":[103],"need":[105],"prompt":[109,149],"specifically":[111],"designed":[112],"illustrating":[117],"how":[118],"VidProM":[119,175],"differs":[120],"DiffusionDB,":[122],"prompt-gallery":[125],"image":[128],"generation.":[129],"Our":[130],"extensive":[131],"diverse":[133],"also":[135],"opens":[136],"up":[137],"many":[138],"exciting":[139],"research":[141],"areas.":[142],"For":[143],"instance,":[144],"suggest":[146],"exploring":[147],"engineering,":[150],"efficient":[151],"generation,":[153],"copy":[156],"detection":[157],"models":[160],"to":[161],"develop":[162],"better,":[163],"more":[164],"efficient,":[165],"safer":[167],"models.":[168],"project":[170],"(including":[171],"collected":[173],"code)":[178],"at":[182],"https://vidprom.github.io":[183],"under":[184],"CC-BY-NC":[186],"4.0":[187],"License.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":43},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":11}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-11-03T00:00:00"}