{"id":"https://openalex.org/W7160034663","doi":"https://doi.org/10.1109/iccv51701.2025.02155","title":"A Token-Level Text Image Foundation Model for Document Understanding","display_name":"A Token-Level Text Image Foundation Model for Document Understanding","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7160034663","doi":"https://doi.org/10.1109/iccv51701.2025.02155"},"language":null,"primary_location":{"id":"doi:10.1109/iccv51701.2025.02155","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02155","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":["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/A5059748327","display_name":"Tongkun Guan","orcid":"https://orcid.org/0000-0003-3346-8315"},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tongkun Guan","raw_affiliation_strings":["AI Institute, School of Computer Science, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, School of Computer Science, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135238371","display_name":"Zining Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zining Wang","raw_affiliation_strings":["Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135225800","display_name":"Pei Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pei Fu","raw_affiliation_strings":["Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135203817","display_name":"Zhengtao Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengtao Guo","raw_affiliation_strings":["Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021650488","display_name":"Wei Shen","orcid":"https://orcid.org/0000-0002-4002-1207"},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Wei Shen","raw_affiliation_strings":["AI Institute, School of Computer Science, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, School of Computer Science, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135152275","display_name":"Kai Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Zhou","raw_affiliation_strings":["Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063274979","display_name":"Tiezhu Yue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tiezhu Yue","raw_affiliation_strings":["Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135168700","display_name":"Chen Duan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Duan","raw_affiliation_strings":["Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100700666","display_name":"Han Sun","orcid":"https://orcid.org/0009-0002-8186-2376"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Sun","raw_affiliation_strings":["Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073437730","display_name":"Qianyi Jiang","orcid":"https://orcid.org/0000-0002-6006-9929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qianyi Jiang","raw_affiliation_strings":["Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135233483","display_name":"Junfeng Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junfeng Luo","raw_affiliation_strings":["Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135221129","display_name":"Xiaokang Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xiaokang Yang","raw_affiliation_strings":["AI Institute, School of Computer Science, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, School of Computer Science, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence","institution_ids":["https://openalex.org/I4210164862"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23210","last_page":"23220"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9086999893188477,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9086999893188477,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.021299999207258224,"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":0.004800000227987766,"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/foundation","display_name":"Foundation (evidence)","score":0.49729999899864197},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4253000020980835},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.27309998869895935},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.26840001344680786},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.26429998874664307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6032000184059143},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.49729999899864197},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37790000438690186},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32199999690055847},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2849999964237213},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26840001344680786},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25929999351501465}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv51701.2025.02155","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02155","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4115979559","display_name":null,"funder_award_id":"62322604,62176159","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1966382373","https://openalex.org/W2962772269","https://openalex.org/W2963299604","https://openalex.org/W3159481202","https://openalex.org/W3211070770","https://openalex.org/W4255788608","https://openalex.org/W4321194933","https://openalex.org/W4386065412","https://openalex.org/W4386065575","https://openalex.org/W4389519972","https://openalex.org/W4389520321","https://openalex.org/W4390872592","https://openalex.org/W4390873312","https://openalex.org/W4390874575","https://openalex.org/W4393160827","https://openalex.org/W4393906060","https://openalex.org/W4402704527","https://openalex.org/W4402713111","https://openalex.org/W4402716330","https://openalex.org/W4402753874","https://openalex.org/W4402951581","https://openalex.org/W4402961694","https://openalex.org/W4402961917","https://openalex.org/W4404002859","https://openalex.org/W4404239097","https://openalex.org/W4404612908","https://openalex.org/W4404782234","https://openalex.org/W4405416283","https://openalex.org/W4407451030","https://openalex.org/W4409366125","https://openalex.org/W4412887761","https://openalex.org/W4412888667","https://openalex.org/W4412945734","https://openalex.org/W4413146357","https://openalex.org/W7125812135","https://openalex.org/W7133239970"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-05T00:00:00"}
