{"id":"https://openalex.org/W4416522420","doi":"https://doi.org/10.1109/iccv51701.2025.00052","title":"Interpretable Zero-Shot Learning with Locally-Aligned Vision-Language Model","display_name":"Interpretable Zero-Shot Learning with Locally-Aligned Vision-Language Model","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416522420","doi":"https://doi.org/10.1109/iccv51701.2025.00052"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.23822","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073242437","display_name":"Shiming Chen","orcid":"https://orcid.org/0000-0002-3670-5294"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Shiming Chen","raw_affiliation_strings":["Mohamed bin Zayed University of AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of AI","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bowen Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Duan","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012655817","display_name":"Salman A. Khan","orcid":"https://orcid.org/0000-0002-3892-2241"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Salman Khan","raw_affiliation_strings":["Mohamed bin Zayed University of AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of AI","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104250018","display_name":"Fahad Shahbaz Khan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Fahad Shahbaz Khan","raw_affiliation_strings":["Mohamed bin Zayed University of AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of AI","institution_ids":["https://openalex.org/I4210113480"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"478","last_page":"487"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.840499997138977,"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":0.840499997138977,"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":0.11800000071525574,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.007400000002235174,"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/similarity","display_name":"Similarity (geometry)","score":0.6347000002861023},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.534600019454956},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3582000136375427},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3467999994754791},{"id":"https://openalex.org/keywords/similitude","display_name":"Similitude","score":0.34529998898506165},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3249000012874603}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7064999938011169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6877999901771545},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6347000002861023},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.534600019454956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5238000154495239},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30399999022483826},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2802000045776367}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.23822","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.23822","pdf_url":"https://arxiv.org/pdf/2506.23822","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.23822","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.23822","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.23822","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.23822","pdf_url":"https://arxiv.org/pdf/2506.23822","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large-scale":[0],"vision-language":[1,101],"models":[2,59],"(VLMs),":[3],"such":[4],"as":[5,27],"CLIP,":[6],"have":[7],"achieved":[8],"remarkable":[9],"success":[10],"in":[11],"zero-shot":[12],"learning":[13],"(ZSL)":[14],"by":[15,60],"leveraging":[16],"large-scale":[17],"visual-text":[18],"pair":[19],"datasets.":[20],"However,":[21],"these":[22],"methods":[23],"often":[24],"lack":[25],"interpretability,":[26,148],"they":[28],"compute":[29],"the":[30,38,132],"similarity":[31,130],"between":[32,117],"an":[33],"entire":[34],"query":[35],"image":[36],"and":[37,120,127,151],"embedded":[39],"category":[40],"words,":[41],"making":[42],"it":[43],"difficult":[44],"to":[45,51,56,71,80,114],"explain":[46],"their":[47,121],"predictions.":[48],"One":[49],"approach":[50],"address":[52],"this":[53],"issue":[54],"is":[55],"develop":[57],"interpretable":[58,104,129],"integrating":[61],"language,":[62],"where":[63],"classifiers":[64],"are":[65],"built":[66],"using":[67],"discrete":[68],"attributes,":[69,123],"similar":[70],"human":[72],"perception.":[73],"This":[74],"introduces":[75],"a":[76,99],"new":[77],"challenge:":[78],"how":[79],"effectively":[81],"align":[82],"local":[83,108],"visual":[84,118],"features":[85],"with":[86],"corresponding":[87],"attributes":[88],"based":[89],"on":[90],"pre-trained":[91],"VLMs.":[92],"To":[93],"tackle":[94],"this,":[95],"we":[96],"propose":[97],"LaZSL,":[98],"locally-aligned":[100],"model":[102],"for":[103,134],"ZSL.":[105],"LaZSL":[106],"employs":[107],"visual-semantic":[109],"alignment":[110,126],"via":[111],"optimal":[112],"transport":[113],"perform":[115],"interaction":[116],"regions":[119],"associated":[122],"facilitating":[124],"effective":[125],"providing":[128],"without":[131],"need":[133],"additional":[135],"training.":[136],"Extensive":[137],"experiments":[138],"demonstrate":[139],"that":[140],"our":[141],"method":[142],"offers":[143],"several":[144],"advantages,":[145],"including":[146],"enhanced":[147],"improved":[149],"accuracy,":[150],"strong":[152],"domain":[153],"generalization.":[154],"Codes":[155],"available":[156],"at:":[157],"https://github.com/shiming-chen/LaZSL.":[158]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}