{"id":"https://openalex.org/W4416039107","doi":"https://doi.org/10.1109/iccv51701.2025.00320","title":"SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning","display_name":"SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416039107","doi":"https://doi.org/10.1109/iccv51701.2025.00320"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00320","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.10252","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100456835","display_name":"Zhi Chen","orcid":"https://orcid.org/0000-0002-9385-144X"},"institutions":[{"id":"https://openalex.org/I185523456","display_name":"University of Southern Queensland","ror":"https://ror.org/04sjbnx57","country_code":"AU","type":"education","lineage":["https://openalex.org/I185523456"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Zhi Chen","raw_affiliation_strings":["University of Southern Queensland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern Queensland","institution_ids":["https://openalex.org/I185523456"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102909275","display_name":"Ziwen Zhao","orcid":"https://orcid.org/0009-0009-6398-6667"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zecheng Zhao","raw_affiliation_strings":["University of Queensland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Queensland","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038505509","display_name":"Jingcai Guo","orcid":"https://orcid.org/0000-0002-0449-4525"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jingcai Guo","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100338386","display_name":"Jingjing Li","orcid":"https://orcid.org/0000-0002-5504-2529"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Li","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102761394","display_name":"Zi Huang","orcid":"https://orcid.org/0000-0002-7187-9425"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zi Huang","raw_affiliation_strings":["University of Queensland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Queensland","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100456835"],"corresponding_institution_ids":["https://openalex.org/I185523456"],"apc_list":null,"apc_paid":null,"fwci":2.0398,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9069088,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3346","last_page":"3356"},"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":0.9869999885559082,"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":0.9869999885559082,"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":0.003800000064074993,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0015999999595806003,"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/ambiguity","display_name":"Ambiguity","score":0.5990999937057495},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5501999855041504},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5296000242233276},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.44440001249313354},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4440000057220459},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.43860000371932983},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.4359000027179718},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.41499999165534973},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.40119999647140503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7972000241279602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6098999977111816},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5990999937057495},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5501999855041504},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5296000242233276},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4918999969959259},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.44440001249313354},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4440000057220459},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.43860000371932983},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.4359000027179718},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.41499999165534973},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.40119999647140503},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.36899998784065247},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3070000112056732},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30660000443458557},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C67277372","wikidata":"https://www.wikidata.org/wiki/Q7449085","display_name":"Semantic role labeling","level":3,"score":0.30309998989105225},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.29019999504089355},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26249998807907104}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00320","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:2503.10252","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10252","pdf_url":"https://arxiv.org/pdf/2503.10252","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2503.10252","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.10252","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.10252","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10252","pdf_url":"https://arxiv.org/pdf/2503.10252","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[{"id":"https://openalex.org/G7889722298","display_name":null,"funder_award_id":"DP240101814","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"learning":[1],"(ZSL)":[2],"aims":[3],"to":[4,37,91,106],"recognize":[5],"unseen":[6],"classes":[7],"without":[8],"labeled":[9],"training":[10],"examples":[11],"by":[12],"leveraging":[13],"class-level":[14],"semantic":[15,26,132],"descriptors":[16],"such":[17],"as":[18],"attributes.":[19],"A":[20],"fundamental":[21],"challenge":[22],"in":[23,32,50,110],"ZSL":[24,171],"is":[25,115,190],"misalignment,":[27],"where":[28],"semantic-unrelated":[29,45,68,108,136],"information":[30,46],"involved":[31],"visual":[33],"features":[34],"introduce":[35,79],"ambiguity":[36],"visual-semantic":[38,93],"interaction.":[39],"Unlike":[40],"existing":[41],"methods":[42],"that":[43,103,174],"suppress":[44],"post":[47],"hoc":[48],"either":[49],"the":[51,55,64,73,111,118,139],"feature":[52,166,187],"space":[53],"or":[54],"model":[56],"space,":[57],"we":[58,78,96,146,158],"propose":[59,97],"addressing":[60],"this":[61,76],"issue":[62],"at":[63,192],"input":[65,112,140],"stage,":[66],"preventing":[67],"patches":[69,109,137],"from":[70,120,138,155],"propagating":[71],"through":[72],"network.":[74],"To":[75],"end,":[77],"Semantically":[80],"contextualized":[81],"VIsual":[82],"Patches":[83],"(SVIP)":[84],"for":[85],"ZSL,":[86],"a":[87,98],"transformer-based":[88],"framework":[89],"designed":[90],"enhance":[92],"alignment.":[94],"Specifically,":[95],"self-supervised":[99],"patch":[100,151],"selection":[101],"mechanism":[102],"preemptively":[104],"learns":[105],"identify":[107],"space.":[113],"This":[114],"trained":[116],"with":[117,149],"supervision":[119],"aggregated":[121],"attention":[122],"scores":[123],"across":[124],"all":[125],"transformer":[126],"layers,":[127],"which":[128],"estimate":[129],"each":[130],"patch's":[131],"score.":[133],"As":[134],"removing":[135],"sequence":[141],"may":[142],"disrupt":[143],"object":[144],"structure,":[145],"replace":[147],"them":[148],"learnable":[150],"embeddings.":[152],"With":[153],"initialization":[154],"word":[156],"embeddings,":[157],"can":[159],"ensure":[160],"they":[161],"remain":[162],"semantically":[163,185],"meaningful":[164],"throughout":[165],"extraction.":[167],"Extensive":[168],"experiments":[169],"on":[170],"benchmarks":[172],"demonstrate":[173],"SVIP":[175],"achieves":[176],"state-of-the-art":[177],"performance":[178],"results":[179],"while":[180],"providing":[181],"more":[182],"interpretable":[183],"and":[184],"rich":[186],"representations.":[188],"Code":[189],"available":[191],"https://github.com/uqzhichen/SVIP.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}