{"id":"https://openalex.org/W4413278588","doi":"https://doi.org/10.1109/icip55913.2025.11084286","title":"Holism To Atomism: Enhancing The Vision-Language Alignment For Cross-Modal Few-Shot Learning","display_name":"Holism To Atomism: Enhancing The Vision-Language Alignment For Cross-Modal Few-Shot Learning","publication_year":2025,"publication_date":"2025-08-18","ids":{"openalex":"https://openalex.org/W4413278588","doi":"https://doi.org/10.1109/icip55913.2025.11084286"},"language":"en","primary_location":{"id":"doi:10.1109/icip55913.2025.11084286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip55913.2025.11084286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing (ICIP)","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/A5100758437","display_name":"Boyu Yang","orcid":"https://orcid.org/0000-0002-6338-0456"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyu Yang","raw_affiliation_strings":["China Mobile Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100416260","display_name":"Mingjie Li","orcid":"https://orcid.org/0000-0002-2989-2669"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjie Li","raw_affiliation_strings":["China Mobile Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074679809","display_name":"Xi Chen","orcid":"https://orcid.org/0000-0001-9223-0302"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Chen","raw_affiliation_strings":["China Mobile Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420654","display_name":"Liang Li","orcid":"https://orcid.org/0000-0002-1943-8219"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Li","raw_affiliation_strings":["China Mobile Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103057360","display_name":"Chao Deng","orcid":"https://orcid.org/0000-0003-4971-930X"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Deng","raw_affiliation_strings":["China Mobile Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079750750","display_name":"Junlan Feng","orcid":"https://orcid.org/0000-0001-5292-2945"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junlan Feng","raw_affiliation_strings":["China Mobile Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute","institution_ids":["https://openalex.org/I180662265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I180662265"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16993863,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2642","last_page":"2647"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.8920000195503235,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.8920000195503235,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8277999758720398,"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/holism","display_name":"Holism","score":0.8625574111938477},{"id":"https://openalex.org/keywords/atomism","display_name":"Atomism","score":0.8520694971084595},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6103073954582214},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5205605626106262},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4316471219062805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38345980644226074},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.37317711114883423},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.21169042587280273},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.18784686923027039},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.18287742137908936},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.14763063192367554}],"concepts":[{"id":"https://openalex.org/C20155586","wikidata":"https://www.wikidata.org/wiki/Q192891","display_name":"Holism","level":2,"score":0.8625574111938477},{"id":"https://openalex.org/C37586779","wikidata":"https://www.wikidata.org/wiki/Q178668","display_name":"Atomism","level":2,"score":0.8520694971084595},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6103073954582214},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5205605626106262},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4316471219062805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38345980644226074},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.37317711114883423},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.21169042587280273},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.18784686923027039},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.18287742137908936},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.14763063192367554},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip55913.2025.11084286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip55913.2025.11084286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2963350370","https://openalex.org/W2963943197","https://openalex.org/W2964105864","https://openalex.org/W3012255272","https://openalex.org/W3034251792","https://openalex.org/W3035370595","https://openalex.org/W3095388829","https://openalex.org/W3108189450","https://openalex.org/W3131068231","https://openalex.org/W3198377975","https://openalex.org/W3198675127","https://openalex.org/W4229453513","https://openalex.org/W4312310776","https://openalex.org/W4386057727","https://openalex.org/W4386075985","https://openalex.org/W4386076681","https://openalex.org/W4390872642"],"related_works":["https://openalex.org/W1534347869","https://openalex.org/W1564309909","https://openalex.org/W3199813748","https://openalex.org/W1987919060","https://openalex.org/W1483183840","https://openalex.org/W4234792971","https://openalex.org/W2147555626","https://openalex.org/W4234819803","https://openalex.org/W4239259544","https://openalex.org/W2896199958"],"abstract_inverted_index":{"Few-shot":[0],"learning":[1],"has":[2],"made":[3],"substantial":[4],"progress":[5],"due":[6],"to":[7,62,96,102,148],"the":[8,17,22,26,29,34,37,41,72,76,81,89,97,104,111,115,122,130,136,142,149,155,166,171],"pre-trained":[9],"cross-modal":[10],"models,":[11],"e.g.,":[12],"CLIP,":[13],"which":[14],"contrastively":[15],"align":[16],"vision-language":[18],"pairs.":[19],"Simply":[20],"aligning":[21],"class":[23,157],"token":[24],"of":[25],"image":[27,107,124,137],"with":[28,75,154],"associated":[30],"text":[31],"suffers":[32],"from":[33],"challenge,":[35],"that":[36,165],"intrinsic":[38],"mismatch":[39,65],"between":[40,84,117],"vision":[42,73,91],"and":[43,86,121,177],"language":[44,77],"features":[45],"in":[46,100],"a":[47,57],"given":[48,105],"pair":[49],"is":[50,126],"ignored.":[51],"In":[52],"this":[53,64],"study,":[54],"we":[55],"propose":[56],"Holism-to-Atomism":[58],"approach,":[59],"called":[60],"H2A,":[61],"address":[63],"challenge.":[66],"During":[67,140],"training,":[68],"it":[69],"first":[70],"aligns":[71],"patches":[74,85,92,120,125],"tokens":[78],"by":[79,128],"determining":[80],"similarity":[82,98],"matrix":[83],"tokens.":[87],"Meanwhile,":[88],"refined":[90,119],"are":[93,145],"scratched":[94],"according":[95,147],"matrix,":[99],"order":[101],"represent":[103],"training":[106],"compactly":[108],"while":[109],"removing":[110],"redundant":[112],"patches.":[113],"Then,":[114],"alignment":[116],"those":[118],"other":[123],"implemented,":[127],"calculating":[129],"patch-based":[131,150],"prediction":[132,151],"probability":[133,152],"based":[134],"on":[135,161,175],"patch":[138],"similarity.":[139],"inference,":[141],"queried":[143],"images":[144],"classified":[146],"combined":[153],"existing":[156],"token-based":[158],"one.":[159],"Experiments":[160],"11":[162],"datasets":[163],"show":[164],"H2A":[167],"significantly":[168],"improves":[169],"upon":[170],"baseline":[172],"approaches":[173],"especially":[174],"8-shot":[176],"16-shot.":[178]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}