{"id":"https://openalex.org/W4317384342","doi":"https://doi.org/10.1109/access.2023.3237966","title":"A Cross-Modal Alignment for Zero-Shot Image Classification","display_name":"A Cross-Modal Alignment for Zero-Shot Image Classification","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4317384342","doi":"https://doi.org/10.1109/access.2023.3237966"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3237966","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3237966","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10018960.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10018960.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045608624","display_name":"Lu Wu","orcid":"https://orcid.org/0000-0002-1780-6823"},"institutions":[{"id":"https://openalex.org/I211433327","display_name":"Ministry of Natural Resources","ror":"https://ror.org/02kxqx159","country_code":"CN","type":"funder","lineage":["https://openalex.org/I211433327","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lu Wu","raw_affiliation_strings":["Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, Shenzhen, China","School of Information Engineering, Wuhan University of Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, Shenzhen, China","institution_ids":["https://openalex.org/I211433327"]},{"raw_affiliation_string":"School of Information Engineering, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012830181","display_name":"Chenyu Wu","orcid":"https://orcid.org/0000-0002-6450-6268"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyu Wu","raw_affiliation_strings":["School of Information Engineering, Wuhan University of Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101811812","display_name":"Han Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I211433327","display_name":"Ministry of Natural Resources","ror":"https://ror.org/02kxqx159","country_code":"CN","type":"funder","lineage":["https://openalex.org/I211433327","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Guo","raw_affiliation_strings":["Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, Shenzhen, China","School of Resource and Environmental Sciences, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, Shenzhen, China","institution_ids":["https://openalex.org/I211433327"]},{"raw_affiliation_string":"School of Resource and Environmental Sciences, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100762170","display_name":"Zhihao Zhao","orcid":"https://orcid.org/0000-0001-5944-9687"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Zhao","raw_affiliation_strings":["School of Information Engineering, Wuhan University of Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5045608624"],"corresponding_institution_ids":["https://openalex.org/I196699116","https://openalex.org/I211433327"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.8741,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77335151,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"11","issue":null,"first_page":"9067","last_page":"9073"},"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9983000159263611,"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":0.9897000193595886,"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/computer-science","display_name":"Computer science","score":0.7437593340873718},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6386517286300659},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6272303462028503},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.591412365436554},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5789980292320251},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5353792905807495},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5266233086585999},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5182485580444336},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.47421979904174805},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4741377532482147},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44692888855934143},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4444604516029358},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.42211514711380005},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4174952805042267},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41088995337486267},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2488342523574829},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21014434099197388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7437593340873718},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6386517286300659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6272303462028503},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.591412365436554},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5789980292320251},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5353792905807495},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5266233086585999},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5182485580444336},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.47421979904174805},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4741377532482147},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44692888855934143},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4444604516029358},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.42211514711380005},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4174952805042267},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41088995337486267},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2488342523574829},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21014434099197388},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3237966","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3237966","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10018960.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:45816bdc2cbe4e768ad20fc766d361fb","is_oa":true,"landing_page_url":"https://doaj.org/article/45816bdc2cbe4e768ad20fc766d361fb","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 9067-9073 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3237966","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3237966","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10018960.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310282","display_name":"Ministry of Natural Resources","ror":"https://ror.org/02ntv3742"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4317384342.pdf","grobid_xml":"https://content.openalex.org/works/W4317384342.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W43954826","https://openalex.org/W1960364170","https://openalex.org/W2044913453","https://openalex.org/W2141350700","https://openalex.org/W2209594346","https://openalex.org/W2596142952","https://openalex.org/W2601051138","https://openalex.org/W2604272474","https://openalex.org/W2765813195","https://openalex.org/W2905471643","https://openalex.org/W2924476266","https://openalex.org/W2962716320","https://openalex.org/W2962762077","https://openalex.org/W2962903908","https://openalex.org/W2963283377","https://openalex.org/W2963955422","https://openalex.org/W2963960318","https://openalex.org/W2979571231","https://openalex.org/W2982407353","https://openalex.org/W2986692991","https://openalex.org/W2990138404","https://openalex.org/W2991813857","https://openalex.org/W3018953709","https://openalex.org/W3034730995","https://openalex.org/W3035655772","https://openalex.org/W3143107425","https://openalex.org/W3171926364","https://openalex.org/W3176716813","https://openalex.org/W3182605419","https://openalex.org/W3203055845","https://openalex.org/W6678470764","https://openalex.org/W6751281049","https://openalex.org/W6754700304","https://openalex.org/W6767354860","https://openalex.org/W6767668836","https://openalex.org/W6781630272","https://openalex.org/W6785403945","https://openalex.org/W6802136708"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W4390516098","https://openalex.org/W2037549926","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2142795561","https://openalex.org/W2849310602","https://openalex.org/W4205302943"],"abstract_inverted_index":{"Different":[0],"from":[1,30],"major":[2],"classification":[3],"methods":[4,116,122],"based":[5],"on":[6],"large":[7],"amounts":[8],"of":[9,26,76,91],"annotation":[10],"data,":[11],"we":[12],"introduce":[13],"a":[14],"cross-modal":[15],"alignment":[16],"for":[17],"zero-shot":[18],"image":[19],"classification.The":[20],"key":[21],"is":[22,45,63,84],"utilizing":[23],"the":[24,31,74,80,88,92,105],"query":[25,75],"text":[27,57,77,93],"attribute":[28,94],"learned":[29],"seen":[32],"classes":[33],"to":[34,47,65,86],"guide":[35],"local":[36],"feature":[37,70,98],"responses":[38],"in":[39,114,123],"unseen":[40],"classes.":[41],"First,":[42],"an":[43,60],"encoder":[44],"used":[46,64,85],"align":[48],"semantic":[49],"matching":[50,89],"between":[51],"visual":[52],"features":[53],"and":[54,95],"their":[55],"corresponding":[56,97],"attribute.":[58,78],"Second,":[59],"attention":[61],"module":[62],"get":[66,107],"response":[67],"maps":[68,71],"through":[69],"activated":[72],"by":[73],"Finally,":[79],"cosine":[81],"distance":[82],"metric":[83],"measure":[87],"degree":[90],"its":[96],"response.":[99],"The":[100],"experiment":[101],"results":[102],"show":[103],"that":[104],"method":[106],"better":[108],"performance":[109],"than":[110],"existing":[111],"Zero-shot":[112],"Learning":[113],"embedding-based":[115],"as":[117,119],"well":[118],"other":[120],"generative":[121],"CUB-200-2011":[124],"dataset.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}