{"id":"https://openalex.org/W7118185822","doi":"https://doi.org/10.1145/3785474","title":"TextCoT: Zoom-In for Enhanced Multimodal Text-Rich Image Understanding","display_name":"TextCoT: Zoom-In for Enhanced Multimodal Text-Rich Image Understanding","publication_year":2026,"publication_date":"2026-01-05","ids":{"openalex":"https://openalex.org/W7118185822","doi":"https://doi.org/10.1145/3785474"},"language":"en","primary_location":{"id":"doi:10.1145/3785474","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3785474","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5102518828","display_name":"Bozhi Luan","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bozhi Luan","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0005-6554-1187","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121944173","display_name":"Hao Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Feng","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-8127-6639","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121958871","display_name":"Hong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1304921434","display_name":"Consumers Union","ror":"https://ror.org/056j68a95","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1304921434"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Chen","raw_affiliation_strings":["Merchants Union Consumer Finance Company Limited, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0008-4283-1917","affiliations":[{"raw_affiliation_string":"Merchants Union Consumer Finance Company Limited, Shenzhen, China","institution_ids":["https://openalex.org/I1304921434"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yonghui Wang","orcid":"https://orcid.org/0000-0002-4741-8231"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghui Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-4741-8231","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121952982","display_name":"Wengang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wengang Zhou","raw_affiliation_strings":["EEIS Department, University of Science and Technology of\u00a0China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1690-9836","affiliations":[{"raw_affiliation_string":"EEIS Department, University of Science and Technology of\u00a0China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004125857","display_name":"HouQiang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Houqiang Li","raw_affiliation_strings":["EEIS Department, University of Science and Technology of\u00a0China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-2188-3028","affiliations":[{"raw_affiliation_string":"EEIS Department, University of Science and Technology of\u00a0China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":19.7937,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.98448042,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"22","issue":"4","first_page":"1","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9818999767303467,"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":0.9818999767303467,"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/T10028","display_name":"Topic Modeling","score":0.003599999938160181,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.002199999988079071,"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/closed-captioning","display_name":"Closed captioning","score":0.9093000292778015},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6665999889373779},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5992000102996826},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.46700000762939453},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.42340001463890076},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.384799987077713},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.32409998774528503}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9093000292778015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9014999866485596},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6665999889373779},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5992000102996826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48890000581741333},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.46700000762939453},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4426000118255615},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42340001463890076},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.32409998774528503},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.31869998574256897},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3043999969959259},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2919999957084656},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3785474","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3785474","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.46457335352897644}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2277195237","https://openalex.org/W2979382951","https://openalex.org/W3174746398","https://openalex.org/W4399785296"],"related_works":[],"abstract_inverted_index":{"The":[0,113],"advent":[1],"of":[2,29],"Large":[3],"Multimodal":[4],"Models":[5],"(LMMs)":[6],"has":[7],"fueled":[8],"extensive":[9],"research":[10],"due":[11],"to":[12,81],"their":[13],"sophisticated":[14],"reasoning":[15],"capabilities.":[16],"However,":[17],"for":[18,59,90],"understanding":[19,53,84],"text-rich":[20,51],"images,":[21],"challenges":[22],"persist":[23],"in":[24],"fully":[25],"leveraging":[26,55],"the":[27],"potential":[28],"LMMs,":[30],"and":[31,62,76,85,108],"existing":[32],"methods":[33],"struggle":[34],"with":[35],"effectively":[36],"processing":[37],"high-resolution":[38],"images.":[39],"Addressing":[40],"this,":[41],"we":[42],"introduce":[43],"TextCoT,":[44],"a":[45,82],"training-free":[46],"Chain-of-Thought":[47],"framework":[48],"that":[49],"improves":[50],"image":[52],"by":[54],"LMMs\u2019":[56],"captioning":[57],"abilities":[58],"global":[60],"context":[61],"detailed":[63],"local":[64],"textual":[65],"analysis.":[66],"TextCoT":[67],"comprises":[68],"three":[69],"stages:":[70],"Global":[71],"Context":[72],"Generation,":[73],"Macro-Scale":[74],"Positioning,":[75],"Fine-Grained":[77],"Visual":[78],"Inspection\u2014each":[79],"contributing":[80],"comprehensive":[83],"precise":[86],"information":[87],"extraction":[88],"needed":[89],"accurate":[91],"question-answering.":[92],"Our":[93],"method":[94],"requires":[95],"no":[96],"additional":[97],"training,":[98],"offering":[99],"immediate":[100],"plug-and-play":[101],"functionality.":[102],"We":[103],"have":[104],"demonstrated":[105],"TextCoT\u2019s":[106],"effectiveness":[107],"adaptability":[109],"across":[110],"various":[111],"benchmarks.":[112],"source":[114],"code":[115],"is":[116],"available":[117],"at":[118],"https://github.com/bzluan/TextCoT":[119],".":[120]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-01-05T00:00:00"}
