{"id":"https://openalex.org/W4414752452","doi":"https://doi.org/10.1007/s11432-024-4603-x","title":"Consistent multimodal pre-training for visual tokenization","display_name":"Consistent multimodal pre-training for visual tokenization","publication_year":2025,"publication_date":"2025-09-28","ids":{"openalex":"https://openalex.org/W4414752452","doi":"https://doi.org/10.1007/s11432-024-4603-x"},"language":"en","primary_location":{"id":"doi:10.1007/s11432-024-4603-x","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11432-024-4603-x","pdf_url":null,"source":{"id":"https://openalex.org/S4210218743","display_name":"Science China Information Sciences","issn_l":"1674-733X","issn":["1674-733X","1869-1919"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Science China Information Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100783702","display_name":"Ting Pan","orcid":"https://orcid.org/0000-0002-4199-4756"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Pan","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence, Beijing, 100083, China","Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100086, China","School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, 100049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence, Beijing, 100083, China","institution_ids":["https://openalex.org/I4210100255"]},{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100086, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103231924","display_name":"Lulu Tang","orcid":"https://orcid.org/0000-0003-2362-1363"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lulu Tang","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence, Beijing, 100083, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence, Beijing, 100083, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100653846","display_name":"Xinlong Wang","orcid":"https://orcid.org/0000-0002-8137-1692"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinlong Wang","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence, Beijing, 100083, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence, Beijing, 100083, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352321","display_name":"Xin Liu","orcid":"https://orcid.org/0000-0003-2802-594X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xin Liu","raw_affiliation_strings":["SeetaCloud, Nanjing, 210000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SeetaCloud, Nanjing, 210000, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050297728","display_name":"Shiguang Shan","orcid":"https://orcid.org/0000-0002-8348-392X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shiguang Shan","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100086, China","School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, 100049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100086, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050297728","https://openalex.org/A5100352321"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176","https://openalex.org/I4210165038"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23589661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"68","issue":"10","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":0.9988999962806702,"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":0.9988999962806702,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9983000159263611,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9980999827384949,"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-language","display_name":"Visual language","score":0.5331000089645386},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4887999892234802},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.45980000495910645},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.3928000032901764},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.3547999858856201},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.3418999910354614}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7501999735832214},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.5331000089645386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5277000069618225},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4925999939441681},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4887999892234802},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.45980000495910645},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3659999966621399},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3547999858856201},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2888000011444092}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11432-024-4603-x","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11432-024-4603-x","pdf_url":null,"source":{"id":"https://openalex.org/S4210218743","display_name":"Science China Information Sciences","issn_l":"1674-733X","issn":["1674-733X","1869-1919"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Science China Information Sciences","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2150884987","https://openalex.org/W2186222003","https://openalex.org/W2277195237","https://openalex.org/W4288083516","https://openalex.org/W4306820534","https://openalex.org/W4327519267","https://openalex.org/W4361194507","https://openalex.org/W4366208220","https://openalex.org/W4383987918","https://openalex.org/W4383996771","https://openalex.org/W4385473806","https://openalex.org/W4387687151","https://openalex.org/W4387947074","https://openalex.org/W4388979610","https://openalex.org/W4390092948","https://openalex.org/W4392011716","https://openalex.org/W4392678661","https://openalex.org/W4392873997","https://openalex.org/W4405595839"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}
