{"id":"https://openalex.org/W4416036165","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.721","title":"Advancing Fine-Grained Visual Understanding with Multi-Scale Alignment in Multi-Modal Models","display_name":"Advancing Fine-Grained Visual Understanding with Multi-Scale Alignment in Multi-Modal Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036165","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.721"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.721","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.721","pdf_url":"https://aclanthology.org/2025.emnlp-main.721.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.721.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062626210","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-4123-8280"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wei Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008593161","display_name":"Zhaowei Li","orcid":"https://orcid.org/0000-0002-5176-4655"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaowei Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101575688","display_name":"Qi Xu","orcid":"https://orcid.org/0000-0002-3951-3298"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343206","display_name":"Linfeng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linfeng Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039898799","display_name":"Yiqing Cai","orcid":"https://orcid.org/0000-0001-7315-0024"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"YiQing Cai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111090176","display_name":"Botian Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Botian Jiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101687248","display_name":"Hang Song","orcid":"https://orcid.org/0000-0002-6470-0976"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hang Song","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113012234","display_name":"Xingcan Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingcan Hu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100317580","display_name":"Pengyu Wang","orcid":"https://orcid.org/0000-0003-4581-9004"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengyu Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Li Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Xiao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5062626210"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32585021,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14282","last_page":"14301"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5914999842643738,"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":0.5914999842643738,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.13369999825954437,"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":0.0778999999165535,"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/natural","display_name":"Natural (archaeology)","score":0.4449000060558319},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41339999437332153},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.36579999327659607},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.301800012588501},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.2660999894142151}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5956000089645386},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4449000060558319},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42739999294281006},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41339999437332153},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3239000141620636},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.24549999833106995},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2362000048160553}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.721","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.721","pdf_url":"https://aclanthology.org/2025.emnlp-main.721.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.721","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.721","pdf_url":"https://aclanthology.org/2025.emnlp-main.721.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036165.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Wei":[0],"Wang,":[1,17],"Zhaowei":[2],"Li,":[3,7],"Qi":[4],"Xu,":[5],"Linfeng":[6],"YiQing":[8],"Cai,":[9],"Botian":[10],"Jiang,":[11],"Hang":[12],"Song,":[13],"Xingcan":[14],"Hu,":[15],"Pengyu":[16],"Li":[18],"Xiao.":[19],"Proceedings":[20],"of":[21],"the":[22],"2025":[23],"Conference":[24],"on":[25],"Empirical":[26],"Methods":[27],"in":[28],"Natural":[29],"Language":[30],"Processing.":[31],"2025.":[32]},"counts_by_year":[],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-11-08T00:00:00"}
