{"id":"https://openalex.org/W4410090390","doi":"https://doi.org/10.1145/3696410.3714861","title":"M <sup>2</sup> -VLP: Enhancing Multilingual Vision-Language Pre-Training via Multi-Grained Alignment","display_name":"M <sup>2</sup> -VLP: Enhancing Multilingual Vision-Language Pre-Training via Multi-Grained Alignment","publication_year":2025,"publication_date":"2025-04-22","ids":{"openalex":"https://openalex.org/W4410090390","doi":"https://doi.org/10.1145/3696410.3714861"},"language":"en","primary_location":{"id":"doi:10.1145/3696410.3714861","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714861","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714861","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 ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714861","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092501202","display_name":"Ahtamjan Ahmat","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140689","display_name":"Technical Institute of Physics and Chemistry","ror":"https://ror.org/04akaak77","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210140689"]},{"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":"Ahtamjan Ahmat","raw_affiliation_strings":["Xinjiang Technical Institute of Physics &amp; Chemistry, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang Technical Institute of Physics &amp; Chemistry, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210140689","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100435750","display_name":"Lei Wang","orcid":"https://orcid.org/0000-0001-6685-0858"},"institutions":[{"id":"https://openalex.org/I4210106108","display_name":"Xinjiang Technical Institute of Physics & Chemistry","ror":"https://ror.org/00x44h034","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210106108"]},{"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":"Lei Wang","raw_affiliation_strings":["Xinjiang Technical Institute of Physics &amp; Chemistry, Chinese Academy of Sciences, Beijing, China, University of Chinese Academy of Sciences, Beijing, China, and Xinjiang Laboratory of Minority Speech and Language Information Processing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang Technical Institute of Physics &amp; Chemistry, Chinese Academy of Sciences, Beijing, China, University of Chinese Academy of Sciences, Beijing, China, and Xinjiang Laboratory of Minority Speech and Language Information Processing, Beijing, China","institution_ids":["https://openalex.org/I4210106108","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034313244","display_name":"Yating Yang","orcid":"https://orcid.org/0000-0002-2639-3944"},"institutions":[{"id":"https://openalex.org/I4210106108","display_name":"Xinjiang Technical Institute of Physics & Chemistry","ror":"https://ror.org/00x44h034","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210106108"]},{"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":"Yating Yang","raw_affiliation_strings":["Xinjiang Technical Institute of Physics &amp; Chemistry, Chinese Academy of Sciences, Beijing, China, University of Chinese Academy of Sciences, Beijing, China, and Xinjiang Laboratory of Minority Speech and Language Information Processing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang Technical Institute of Physics &amp; Chemistry, Chinese Academy of Sciences, Beijing, China, University of Chinese Academy of Sciences, Beijing, China, and Xinjiang Laboratory of Minority Speech and Language Information Processing, Beijing, China","institution_ids":["https://openalex.org/I4210106108","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101910437","display_name":"Bo Ma","orcid":"https://orcid.org/0000-0003-3082-648X"},"institutions":[{"id":"https://openalex.org/I4210106108","display_name":"Xinjiang Technical Institute of Physics & Chemistry","ror":"https://ror.org/00x44h034","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210106108"]},{"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":"Bo Ma","raw_affiliation_strings":["Xinjiang Technical Institute of Physics &amp; Chemistry, Chinese Academy of Sciences, Beijing, China, University of Chinese Academy of Sciences, Beijing, China, and Xinjiang Laboratory of Minority Speech and Language Information Processing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang Technical Institute of Physics &amp; Chemistry, Chinese Academy of Sciences, Beijing, China, University of Chinese Academy of Sciences, Beijing, China, and Xinjiang Laboratory of Minority Speech and Language Information Processing, Beijing, China","institution_ids":["https://openalex.org/I4210106108","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004378974","display_name":"Rui Dong","orcid":"https://orcid.org/0000-0002-4110-3976"},"institutions":[{"id":"https://openalex.org/I4210106108","display_name":"Xinjiang Technical Institute of Physics & Chemistry","ror":"https://ror.org/00x44h034","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210106108"]},{"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":"Rui Dong","raw_affiliation_strings":["Xinjiang Technical Institute of Physics &amp; Chemistry, Chinese Academy of Sciences, Beijing, China, University of Chinese Academy of Sciences, Beijing, China, and Xinjiang Laboratory of Minority Speech and Language Information Processing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang Technical Institute of Physics &amp; Chemistry, Chinese Academy of Sciences, Beijing, China, University of Chinese Academy of Sciences, Beijing, China, and Xinjiang Laboratory of Minority Speech and Language Information Processing, Beijing, China","institution_ids":["https://openalex.org/I4210106108","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101822021","display_name":"Kaiwen Lu","orcid":"https://orcid.org/0000-0002-6327-9171"},"institutions":[{"id":"https://openalex.org/I4210140689","display_name":"Technical Institute of Physics and Chemistry","ror":"https://ror.org/04akaak77","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210140689"]},{"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":"Kaiwen Lu","raw_affiliation_strings":["Xinjiang Technical Institute of Physics &amp; Chemistry, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang Technical Institute of Physics &amp; Chemistry, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210140689","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101406959","display_name":"Rong Ma","orcid":"https://orcid.org/0000-0002-2974-0569"},"institutions":[{"id":"https://openalex.org/I4210140689","display_name":"Technical Institute of Physics and Chemistry","ror":"https://ror.org/04akaak77","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210140689"]},{"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":"Rong Ma","raw_affiliation_strings":["Xinjiang Technical Institute of Physics &amp; Chemistry, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang Technical Institute of Physics &amp; Chemistry, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210140689","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112259814","display_name":"Xinyue Wang","orcid":"https://orcid.org/0009-0002-7995-196X"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyue Wang","raw_affiliation_strings":["Hohai University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5092501202"],"corresponding_institution_ids":["https://openalex.org/I4210140689","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07731401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3438","last_page":"3450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9957000017166138,"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":0.98580002784729,"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":0.6540164947509766},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5630666017532349},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4509257674217224},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4494587182998657},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12154921889305115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6540164947509766},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5630666017532349},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4509257674217224},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4494587182998657},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12154921889305115},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3696410.3714861","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714861","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714861","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 ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3696410.3714861","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714861","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714861","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 ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4410090390.pdf"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2187089797","https://openalex.org/W2481240925","https://openalex.org/W2616247523","https://openalex.org/W2963527096","https://openalex.org/W2963778889","https://openalex.org/W2963909453","https://openalex.org/W3035390927","https://openalex.org/W3100198908","https://openalex.org/W3102564565","https://openalex.org/W3152788712","https://openalex.org/W3171975879","https://openalex.org/W3174010726","https://openalex.org/W3200050180","https://openalex.org/W4385565483","https://openalex.org/W4385569915","https://openalex.org/W4385571469","https://openalex.org/W4385573782","https://openalex.org/W4386083050","https://openalex.org/W4396736086","https://openalex.org/W4396758705"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Recently,":[0],"multilingual":[1,117],"Vision-Language":[2,48],"Pre-training":[3,49],"(mVLP)":[4],"has":[5],"shown":[6],"remarkable":[7],"progress":[8],"in":[9],"learning":[10,110],"joint":[11],"representations":[12],"across":[13,125],"different":[14,36,60],"modalities":[15],"and":[16,29,38,77,90,100,115,138],"languages.":[17],"However,":[18],"most":[19],"existing":[20],"methods":[21],"learn":[22,55],"semantic":[23,61],"alignment":[24,58,72,102],"at":[25,59,142],"a":[26,45,106],"coarse-grained":[27],"level":[28],"fail":[30],"to":[31,54],"capture":[32],"fine-grained":[33],"correlations":[34],"between":[35],"languages":[37,127],"modalities.":[39],"To":[40,96],"address":[41],"this,":[42],"we":[43,104],"propose":[44,105],"Multi-grained":[46],"Multilingual":[47],"(M2-VLP)":[50],"model,":[51],"which":[52],"aims":[53],"cross-lingual":[56,65,99,114],"cross-modal":[57,82,101],"granular":[62],"levels.":[63],"In":[64,81],"interaction,":[66,83],"the":[67,70,78,84,98,129],"model":[68,85],"learns":[69],"global":[71],"of":[73,131],"parallel":[74],"sentence":[75],"pairs":[76],"word-level":[79],"correlations.":[80],"aligns":[86],"images":[87],"with":[88,93],"captions":[89],"image":[91],"regions":[92],"corresponding":[94],"words.":[95],"integrate":[97],"above,":[103],"unified":[107],"multi-grained":[108],"contrastive":[109,135],"paradigm.":[111],"Under":[112],"zero-shot":[113],"fine-tuned":[116],"settings,":[118],"extensive":[119],"experiments":[120],"on":[121],"vision-language":[122],"downstream":[123],"tasks":[124],"twenty":[126],"demonstrate":[128],"effectiveness":[130],"M2-VLP":[132],"over":[133],"competitive":[134],"models.":[136],"Code":[137],"models":[139],"are":[140],"available":[141],"https://github.com/ahtamjan/M2-VLP.":[143]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
