{"id":"https://openalex.org/W4404404779","doi":"https://doi.org/10.1109/iccv51701.2025.01382","title":"TIP-I2V: A Million-Scale Real Text and Image Prompt Dataset for Image-to-Video Generation","display_name":"TIP-I2V: A Million-Scale Real Text and Image Prompt Dataset for Image-to-Video Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404404779","doi":"https://doi.org/10.1109/iccv51701.2025.01382"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01382","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.04709","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074206728","display_name":"Wenhao Wang","orcid":"https://orcid.org/0000-0002-5779-9808"},"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"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wenhao Wang","raw_affiliation_strings":["University of Technology Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Sydney","institution_ids":["https://openalex.org/I114017466"]}]},{"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/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00104568,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14898","last_page":"14908"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9908999800682068,"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":0.9908999800682068,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.972599983215332,"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":0.9702000021934509,"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/image","display_name":"Image (mathematics)","score":0.711257815361023},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6304954290390015},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5858978033065796},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5306854248046875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5018353462219238},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4042320251464844},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.18759343028068542},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.14595606923103333}],"concepts":[{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.711257815361023},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6304954290390015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5858978033065796},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5306854248046875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5018353462219238},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4042320251464844},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.18759343028068542},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.14595606923103333}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01382","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.04709","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.04709","pdf_url":"https://arxiv.org/pdf/2411.04709","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,"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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.04709","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.04709","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.04709","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.04709","pdf_url":"https://arxiv.org/pdf/2411.04709","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,"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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Video":[0],"generation":[1],"models":[2,9,28],"are":[3],"revolutionizing":[4],"content":[5],"creation,":[6],"with":[7,178],"image-to-video":[8,81,124,167,187],"drawing":[10],"increasing":[11],"attention":[12],"due":[13],"to":[14,101,128,139,153],"their":[15,25,149],"enhanced":[16],"controllability,":[17],"visual":[18],"consistency,":[19],"and":[20,33,36,64,89,108,116,143,152,175],"practical":[21],"applications.":[22],"However,":[23],"despite":[24],"popularity,":[26],"these":[27,45],"rely":[29],"on":[30,160],"user-provided":[31,62],"text":[32],"image":[34],"prompts,":[35],"there":[37],"is":[38,192],"currently":[39],"no":[40],"dedicated":[41],"dataset":[42,56,120],"for":[43,68],"studying":[44],"prompts.":[46],"In":[47],"this":[48,94],"paper,":[49],"we":[50,72,98],"introduce":[51],"TIP-I2V,":[52],"the":[53,74,87,135,145,162,176,182],"first":[54],"large-scale":[55,95],"of":[57,92,148,184],"over":[58],"1.70":[59],"million":[60],"unique":[61],"Text":[63],"Image":[65],"Prompts":[66],"specifically":[67],"Image-to-Video":[69],"generation.":[70],"Additionally,":[71],"provide":[73],"corresponding":[75],"generated":[76],"videos":[77],"from":[78],"five":[79],"state-of-the-art":[80],"models.":[82,168],"We":[83],"begin":[84],"by":[85,166,173],"outlining":[86],"time-consuming":[88],"costly":[90],"process":[91],"curating":[93],"dataset.":[96,189],"Next,":[97],"compare":[99],"TIP-I2V":[100,138,174],"two":[102],"popular":[103],"prompt":[104,188],"datasets,":[105],"VidProM":[106],"(text-to-video)":[107],"DiffusionDB":[109],"(text-to-image),":[110],"highlighting":[111],"differences":[112,177],"in":[113,123,137],"both":[114],"basic":[115],"semantic":[117],"information.":[118],"This":[119],"enables":[121],"advancements":[122],"research.":[125],"For":[126],"instance,":[127],"develop":[129],"better":[130],"models,":[131],"researchers":[132],"can":[133],"use":[134],"prompts":[136],"analyze":[140],"user":[141],"preferences":[142],"evaluate":[144],"multi-dimensional":[146],"performance":[147],"trained":[150],"models;":[151],"enhance":[154],"model":[155],"safety,":[156],"they":[157],"may":[158],"focus":[159],"addressing":[161],"misinformation":[163],"issue":[164],"caused":[165],"The":[169,190],"new":[170],"research":[171],"inspired":[172],"existing":[179],"datasets":[180],"emphasize":[181],"importance":[183],"a":[185],"specialized":[186],"project":[191],"available":[193],"at":[194],"https://tip-i2v.github.io.":[195]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}