{"id":"https://openalex.org/W4406032893","doi":"https://doi.org/10.1109/iccv51701.2025.00442","title":"2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining","display_name":"2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4406032893","doi":"https://doi.org/10.1109/iccv51701.2025.00442"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00442","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/2501.00958","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100457807","display_name":"Wenqi Zhang","orcid":"https://orcid.org/0000-0002-8312-0184"},"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":"Wenqi Zhang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438478","display_name":"Hang Zhang","orcid":"https://orcid.org/0000-0003-2514-0811"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hang Zhang","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101967530","display_name":"Xin Li","orcid":"https://orcid.org/0000-0002-8169-6059"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["DAMO Academy,Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DAMO Academy,Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044176278","display_name":"Jiashuo Sun","orcid":null},"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":"Jiashuo Sun","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004615610","display_name":"Yongliang Shen","orcid":"https://orcid.org/0000-0003-0975-3554"},"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":"Yongliang Shen","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026310569","display_name":"Weiming L\u00fc","orcid":"https://orcid.org/0000-0003-1561-2467"},"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":"Weiming Lu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101911374","display_name":"Deli Zhao","orcid":"https://orcid.org/0000-0002-8838-578X"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Deli Zhao","raw_affiliation_strings":["DAMO Academy,Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DAMO Academy,Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008666077","display_name":"Yueting Zhuang","orcid":"https://orcid.org/0000-0001-9017-2508"},"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":"Yueting Zhuang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086674741","display_name":"Lidong Bing","orcid":"https://orcid.org/0000-0003-4565-6313"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Lidong Bing","raw_affiliation_strings":["DAMO Academy,Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DAMO Academy,Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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":"4647","last_page":"4658"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13071","display_name":"Digital Storytelling and Education","score":0.8921999931335449,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T13071","display_name":"Digital Storytelling and Education","score":0.8921999931335449,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11935","display_name":"Literacy, Media, and Education","score":0.8791999816894531,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12542","display_name":"Second Language Learning and Teaching","score":0.784600019454956,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5967124700546265},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4384005665779114},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3214242458343506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31048429012298584}],"concepts":[{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5967124700546265},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4384005665779114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3214242458343506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31048429012298584}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00442","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:2501.00958","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.00958","pdf_url":"https://arxiv.org/pdf/2501.00958","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.00958","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.00958","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:2501.00958","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.00958","pdf_url":"https://arxiv.org/pdf/2501.00958","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7036249533","display_name":null,"funder_award_id":"62376245","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406032893.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Compared":[0,143],"to":[1,11,62,110,144],"image-text":[2,34,136,158],"pair":[3],"data,":[4],"interleaved":[5,137,184],"corpora":[6],"enable":[7],"Vision-Language":[8],"Models":[9],"(VLMs)":[10],"understand":[12],"the":[13,43,46,130],"world":[14],"more":[15,151],"naturally":[16],"like":[17,29,172],"humans.":[18],"However,":[19],"such":[20],"existing":[21],"datasets":[22],"are":[23,57,201],"crawled":[24],"from":[25,129],"webpage,":[26],"facing":[27],"challenges":[28],"low":[30],"knowledge":[31,88,127],"density,":[32],"loose":[33],"relations,":[35],"and":[36,119,125,132,156,169,174,189],"poor":[37],"logical":[38],"coherence":[39],"between":[40],"images.":[41],"On":[42],"other":[44],"hand,":[45],"internet":[47],"hosts":[48],"vast":[49],"instructional":[50,98,113],"videos":[51],"(e.g.,":[52],"online":[53],"geometry":[54],"courses)":[55],"that":[56],"widely":[58],"used":[59],"by":[60],"humans":[61],"learn":[63],"foundational":[64,87],"subjects,":[65],"yet":[66],"these":[67],"valuable":[68],"resources":[69],"remain":[70],"underexplored":[71],"in":[72,167,192],"VLM":[73,90],"training.":[74],"In":[75],"this":[76],"paper,":[77],"we":[78,116],"introduce":[79],"a":[80],"high-quality":[81],"\\textbf{multimodal":[82],"textbook}":[83],"corpus":[84,138],"with":[85],"richer":[86,154],"for":[89,196],"pretraining.":[91],"It":[92],"collects":[93],"over":[94],"2.5":[95],"years":[96],"of":[97],"videos,":[99,131],"totaling":[100],"22,000":[101],"class":[102],"hours.":[103],"We":[104],"first":[105],"use":[106],"an":[107,135],"LLM-proposed":[108],"taxonomy":[109],"systematically":[111],"gather":[112],"videos.":[114],"Then":[115],"progressively":[117],"extract":[118],"refine":[120],"visual":[121,188],"(keyframes),":[122],"audio":[123],"(ASR),":[124],"textual":[126,190],"(OCR)":[128],"organize":[133],"as":[134],"based":[139],"on":[140,179],"temporal":[141],"order.":[142],"its":[145,162],"counterparts,":[146],"our":[147,180],"video-centric":[148],"textbook":[149,181],"offers":[150],"coherent":[152],"context,":[153],"knowledge,":[155],"better":[157],"alignment.":[159],"Experiments":[160],"demonstrate":[161],"superb":[163],"pretraining":[164],"performance,":[165],"particularly":[166],"knowledge-":[168],"reasoning-intensive":[170],"tasks":[171],"ScienceQA":[173],"MathVista.":[175],"Moreover,":[176],"VLMs":[177],"pre-trained":[178],"exhibit":[182],"outstanding":[183],"context":[185,195],"awareness,":[186],"leveraging":[187],"cues":[191],"their":[193],"few-shot":[194],"task":[197],"solving.":[198],"Our":[199],"code":[200],"available":[202],"at":[203],"https://github.com/DAMO-NLP-SG/multimodal_textbook.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}