{"id":"https://openalex.org/W4408353449","doi":"https://doi.org/10.1109/icassp49660.2025.10887898","title":"Refiner: Fine-grained Cross-modal Concepts Refinement for Compositional Zero-Shot Learning","display_name":"Refiner: Fine-grained Cross-modal Concepts Refinement for Compositional Zero-Shot Learning","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353449","doi":"https://doi.org/10.1109/icassp49660.2025.10887898"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887898","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100320847","display_name":"Xiao Zhang","orcid":"https://orcid.org/0000-0001-7397-5632"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Zhang","raw_affiliation_strings":["Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058752981","display_name":"Haodong Jing","orcid":"https://orcid.org/0000-0001-6643-7588"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haodong Jing","raw_affiliation_strings":["Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334172","display_name":"Hui Chen","orcid":"https://orcid.org/0000-0002-2735-1068"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Chen","raw_affiliation_strings":["Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101425592","display_name":"Yongqiang Ma","orcid":"https://orcid.org/0000-0002-6063-5601"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongqiang Ma","raw_affiliation_strings":["Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047405956","display_name":"Nanning Zheng","orcid":"https://orcid.org/0000-0003-1608-8257"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nanning Zheng","raw_affiliation_strings":["Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9660000205039978,"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":0.9660000205039978,"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/T11609","display_name":"Geophysical Methods and Applications","score":0.9362000226974487,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7846671342849731},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6893779039382935},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5310022830963135},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4891491234302521},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3400324285030365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3365808129310608},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.1966608762741089},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.10194447636604309},{"id":"https://openalex.org/keywords/metallurgy","display_name":"Metallurgy","score":0.05850464105606079}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7846671342849731},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6893779039382935},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5310022830963135},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4891491234302521},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3400324285030365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3365808129310608},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.1966608762741089},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.10194447636604309},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.05850464105606079},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887898","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1948251820","https://openalex.org/W2093848332","https://openalex.org/W2736809457","https://openalex.org/W2889167066","https://openalex.org/W2963305465","https://openalex.org/W2986385672","https://openalex.org/W3035084814","https://openalex.org/W3158711590","https://openalex.org/W3162332195","https://openalex.org/W3164354101","https://openalex.org/W4226464635","https://openalex.org/W4312400874","https://openalex.org/W4312578829","https://openalex.org/W4385245566","https://openalex.org/W4386065780","https://openalex.org/W4394597571","https://openalex.org/W6630824708","https://openalex.org/W6631190155","https://openalex.org/W6766978945","https://openalex.org/W6784333009","https://openalex.org/W6791353385","https://openalex.org/W6810452849","https://openalex.org/W6846329140"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Recent":[0],"Compositional":[1],"Zero-Shot":[2],"Learning":[3],"(CZSL)":[4],"methods":[5,52],"increasingly":[6],"adopt":[7],"the":[8,14,23,40,81,97,103],"pre-trained":[9],"vision-language":[10],"models":[11],"to":[12,55,88,101,111,117],"capture":[13,89,112],"contextual":[15,31],"relations":[16],"between":[17],"image":[18,86],"and":[19,36,95,148,168],"text":[20],"spaces.":[21],"However,":[22],"single-class-token":[24],"design":[25],"from":[26,33,48],"Transformer-based":[27],"encoder":[28],"inevitably":[29],"captures":[30],"information":[32,99,115,133],"unrelated":[34],"objects":[35],"background,":[37],"thus":[38],"hindering":[39],"modeling":[41],"of":[42,85],"fine-grained":[43,67,82,126],"class-specific":[44],"visual":[45,93,123,143],"features.":[46],"Suffering":[47],"cross-modal":[49,68,98,132],"gap,":[50],"prior":[51],"also":[53],"struggle":[54],"improve":[56],"compositional":[57],"recognition":[58],"performance.":[59],"To":[60],"address":[61],"these":[62],"issues,":[63],"we":[64,135],"propose":[65],"a":[66,137],"concepts":[69,83],"refinement":[70,84],"framework,":[71],"termed":[72],"as":[73],"Refiner,":[74],"which":[75],"comprises":[76],"two":[77],"pivotal":[78],"components:":[79],"(i)":[80],"embeddings":[87,144],"state-object":[90,127],"context":[91,128],"within":[92],"scenes,":[94],"(ii)":[96],"fusion":[100],"mitigate":[102],"modality":[104],"gap.":[105],"By":[106],"leveraging":[107],"learnable":[108],"query":[109],"vectors":[110],"region-specific":[113],"semantic":[114],"pertinent":[116],"composition":[118],"labels,":[119],"our":[120,155],"approach":[121],"refines":[122],"representations":[124],"with":[125,145],"information.":[129],"As":[130],"for":[131],"fusion,":[134],"construct":[136],"robust":[138],"image-to-text":[139],"mapping":[140],"by":[141],"aligning":[142],"states,":[146],"objects,":[147],"compositions,":[149],"respectively.":[150],"Extensive":[151],"experiments":[152],"demonstrate":[153],"that":[154],"Refiner":[156],"achieves":[157],"new":[158],"state-of-the-art":[159],"performance":[160],"across":[161],"all":[162],"popular":[163],"benchmarks":[164],"in":[165],"both":[166],"closed-":[167],"open-world":[169],"settings.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}