{"id":"https://openalex.org/W4405305571","doi":"https://doi.org/10.1109/indin58382.2024.10774475","title":"Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Learning","display_name":"Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Learning","publication_year":2024,"publication_date":"2024-08-18","ids":{"openalex":"https://openalex.org/W4405305571","doi":"https://doi.org/10.1109/indin58382.2024.10774475"},"language":"en","primary_location":{"id":"doi:10.1109/indin58382.2024.10774475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/indin58382.2024.10774475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 22nd International Conference on Industrial Informatics (INDIN)","raw_type":"proceedings-article"},"type":"article","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/A5028260055","display_name":"Weipeng Cao","orcid":"https://orcid.org/0000-0003-2414-6066"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weipeng Cao","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen),Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101268312","display_name":"Xuyang Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuyang Yao","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University,Shenzhen,China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089943764","display_name":"Zhiwu Xu","orcid":"https://orcid.org/0000-0001-6727-440X"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwu Xu","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University,Shenzhen,China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085263461","display_name":"Yinghui Pan","orcid":"https://orcid.org/0000-0001-5715-2855"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinghui Pan","raw_affiliation_strings":["Shenzhen University,National Engineering Laboratory for Big Data System Computing Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University,National Engineering Laboratory for Big Data System Computing Technology,Shenzhen,China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102607853","display_name":"Yixuan Sun","orcid":"https://orcid.org/0009-0002-3199-4143"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yixuan Sun","raw_affiliation_strings":["Stony Brook University,New York,United States"],"affiliations":[{"raw_affiliation_string":"Stony Brook University,New York,United States","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086491465","display_name":"Dachuan Li","orcid":"https://orcid.org/0000-0002-7267-9951"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dachuan Li","raw_affiliation_strings":["Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012906770","display_name":"Bohua Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093205","display_name":"Foxconn (China)","ror":"https://ror.org/00jb92367","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093205","https://openalex.org/I4210108919"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohua Qiu","raw_affiliation_strings":["ZhenDui Industry Artificial Intelligence Co. Ltd,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"ZhenDui Industry Artificial Intelligence Co. Ltd,Shenzhen,China","institution_ids":["https://openalex.org/I4210093205"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082990287","display_name":"Muheng Wei","orcid":"https://orcid.org/0000-0003-1723-2839"},"institutions":[{"id":"https://openalex.org/I4210093205","display_name":"Foxconn (China)","ror":"https://ror.org/00jb92367","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093205","https://openalex.org/I4210108919"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Muheng Wei","raw_affiliation_strings":["ZhenDui Industry Artificial Intelligence Co. Ltd,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"ZhenDui Industry Artificial Intelligence Co. Ltd,Shenzhen,China","institution_ids":["https://openalex.org/I4210093205"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5028260055"],"corresponding_institution_ids":["https://openalex.org/I4210136793"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20983282,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9833999872207642,"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":0.9833999872207642,"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/T12676","display_name":"Machine Learning and ELM","score":0.9372000098228455,"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":0.902899980545044,"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":0.7215884327888489},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6515906453132629},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5966383218765259},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5399757027626038},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5098466277122498},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38743656873703003},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.08432981371879578}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7215884327888489},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6515906453132629},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5966383218765259},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5399757027626038},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5098466277122498},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38743656873703003},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.08432981371879578},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/indin58382.2024.10774475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/indin58382.2024.10774475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 22nd International Conference on Industrial Informatics (INDIN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2070148066","https://openalex.org/W2250539671","https://openalex.org/W2963499153","https://openalex.org/W3045301932","https://openalex.org/W3089446975","https://openalex.org/W3094502228","https://openalex.org/W3171926364","https://openalex.org/W3182605419","https://openalex.org/W3203055845","https://openalex.org/W4200633401","https://openalex.org/W4205932470","https://openalex.org/W4285600264","https://openalex.org/W4295138011","https://openalex.org/W4312661650","https://openalex.org/W4312762894","https://openalex.org/W4312791158","https://openalex.org/W4382466082","https://openalex.org/W4386076660","https://openalex.org/W4386590915","https://openalex.org/W4387968028","https://openalex.org/W4390874575","https://openalex.org/W6791353385","https://openalex.org/W6800053997","https://openalex.org/W6802136708","https://openalex.org/W6803185190"],"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":{"Realizing":[0],"Generalized":[1],"Zero-Shot":[2],"Learning":[3],"(GZSL)":[4],"based":[5],"on":[6,114],"large":[7,21],"models":[8,22],"is":[9],"emerging":[10],"as":[11,23],"a":[12,66,85],"prevailing":[13],"trend.":[14],"However,":[15],"most":[16],"existing":[17],"methods":[18],"merely":[19],"regard":[20],"black":[24],"boxes,":[25],"solely":[26],"leveraging":[27],"the":[28,32,51,100],"features":[29,52,80],"output":[30],"by":[31,61],"final":[33],"layer":[34],"while":[35],"disregarding":[36],"potential":[37],"performance":[38],"enhancements":[39],"from":[40],"other":[41],"layers.":[42],"Indeed,":[43],"numerous":[44],"researchers":[45],"have":[46,122],"visually":[47],"depicted":[48],"variations":[49],"in":[50],"learned":[53],"across":[54,95],"different":[55],"layers":[56],"of":[57,81,93],"neural":[58],"networks.":[59],"Motivated":[60],"this":[62],"observation,":[63],"we":[64],"propose":[65],"Vision":[67],"Transformer":[68],"(ViT)-based":[69],"GZSL":[70],"method":[71],"named":[72],"Depth-Aware":[73],"Multi-Modal":[74],"ViT":[75],"(DAM2ViT),":[76],"which":[77],"exploits":[78],"multi-level":[79],"ViT.":[82],"DAM2ViT":[83,125],"incorporates":[84],"multi-modal":[86],"interaction":[87],"block":[88],"to":[89,103,130],"align":[90],"semantic":[91,109],"information":[92],"categories":[94],"multiple":[96],"layers,":[97],"thereby":[98],"augmenting":[99],"model's":[101],"capacity":[102],"learn":[104],"associations":[105],"between":[106],"visual":[107],"and":[108],"spaces.":[110],"Extensive":[111],"experiments":[112],"conducted":[113],"three":[115],"benchmark":[116],"datasets":[117],"(i.e.,":[118],"CUB,":[119],"SUN,":[120],"AWA2)":[121],"showcased":[123],"that":[124],"achieves":[126],"competitive":[127],"results":[128],"compared":[129],"state-of-the-art":[131],"methods.":[132]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}