{"id":"https://openalex.org/W4412887761","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1023","title":"Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review","display_name":"Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887761","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1023"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1023","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1023","pdf_url":"https://aclanthology.org/2025.findings-acl.1023.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.1023.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108580404","display_name":"Pei Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pei Fu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059748327","display_name":"Tongkun Guan","orcid":"https://orcid.org/0000-0003-3346-8315"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tongkun Guan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100696155","display_name":"Zining Wang","orcid":"https://orcid.org/0009-0007-3818-1037"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zining Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102907192","display_name":"Zhentao Guo","orcid":"https://orcid.org/0009-0000-0242-4059"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhentao Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Chen Duan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Duan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778529","display_name":"Hao Sun","orcid":"https://orcid.org/0000-0003-0951-6428"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Boming Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boming Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000961788","display_name":"Qianyi Jiang","orcid":"https://orcid.org/0009-0008-0042-1880"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qianyi Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324756","display_name":"Jiayao Ma","orcid":"https://orcid.org/0000-0002-0907-2217"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiayao Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048976141","display_name":"Kai Zhou","orcid":"https://orcid.org/0000-0002-7128-5571"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100569639","display_name":"Junfeng Luo","orcid":"https://orcid.org/0009-0008-8315-123X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junfeng Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":"19941","last_page":"19958"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.847100019454956,"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":0.847100019454956,"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":0.7994999885559082,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.7473999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7387850284576416},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5620720386505127},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47743162512779236},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.46241331100463867}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7387850284576416},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5620720386505127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47743162512779236},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.46241331100463867}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1023","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1023","pdf_url":"https://aclanthology.org/2025.findings-acl.1023.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1023","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1023","pdf_url":"https://aclanthology.org/2025.findings-acl.1023.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.550000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887761.pdf","grobid_xml":"https://content.openalex.org/works/W4412887761.grobid-xml"},"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/W3204019825"],"abstract_inverted_index":{"Pei":[0],"Fu,":[1],"Tongkun":[2],"Guan,":[3],"Zining":[4],"Wang,":[5],"Zhentao":[6],"Guo,":[7],"Chen":[8],"Duan,":[9],"Hao":[10],"Sun,":[11],"Boming":[12],"Chen,":[13],"Qianyi":[14],"Jiang,":[15],"Jiayao":[16],"Ma,":[17],"Kai":[18],"Zhou,":[19],"Junfeng":[20],"Luo.":[21],"Findings":[22],"of":[23],"the":[24],"Association":[25],"for":[26],"Computational":[27],"Linguistics:":[28],"ACL":[29],"2025.":[30,31]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
