{"id":"https://openalex.org/W4390705673","doi":"https://doi.org/10.1186/s13640-024-00620-9","title":"Multimodal few-shot classification without attribute embedding","display_name":"Multimodal few-shot classification without attribute embedding","publication_year":2024,"publication_date":"2024-01-10","ids":{"openalex":"https://openalex.org/W4390705673","doi":"https://doi.org/10.1186/s13640-024-00620-9"},"language":"en","primary_location":{"id":"doi:10.1186/s13640-024-00620-9","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1186/s13640-024-00620-9","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13640-024-00620-9.pdf","source":{"id":"https://openalex.org/S153767265","display_name":"EURASIP Journal on Image and Video Processing","issn_l":"1687-5176","issn":["1687-5176","1687-5281"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Image and Video Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1186/s13640-024-00620-9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041511177","display_name":"Jun Qing Chang","orcid":"https://orcid.org/0000-0002-5819-6638"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Jun Qing Chang","raw_affiliation_strings":["Nanyang Technological University, 50 Nanyang Ave, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-5819-6638","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, 50 Nanyang Ave, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009372982","display_name":"Deepu Rajan","orcid":"https://orcid.org/0000-0001-7788-8368"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Deepu Rajan","raw_affiliation_strings":["Nanyang Technological University, 50 Nanyang Ave, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, 50 Nanyang Ave, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063243883","display_name":"Nicholas Vun","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Nicholas Vun","raw_affiliation_strings":["Nanyang Technological University, 50 Nanyang Ave, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, 50 Nanyang Ave, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5041511177"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":{"value":1140,"currency":"GBP","value_usd":1398},"apc_paid":{"value":1140,"currency":"GBP","value_usd":1398},"fwci":0.2778,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5636215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2024","issue":"1","first_page":null,"last_page":null},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.998199999332428,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.941100001335144,"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/interpretability","display_name":"Interpretability","score":0.8425146341323853},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.8371858596801758},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7330524921417236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7248857021331787},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7046962380409241},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6389524936676025},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5207155346870422},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4988131523132324},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4829249083995819},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4450935125350952},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4427059292793274},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.43820804357528687},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4312573969364166},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.41884058713912964},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4125465750694275},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2709989845752716}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8425146341323853},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8371858596801758},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7330524921417236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7248857021331787},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7046962380409241},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6389524936676025},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5207155346870422},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4988131523132324},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4829249083995819},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4450935125350952},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4427059292793274},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.43820804357528687},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4312573969364166},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.41884058713912964},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4125465750694275},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2709989845752716},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/s13640-024-00620-9","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1186/s13640-024-00620-9","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13640-024-00620-9.pdf","source":{"id":"https://openalex.org/S153767265","display_name":"EURASIP Journal on Image and Video Processing","issn_l":"1687-5176","issn":["1687-5176","1687-5281"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Image and Video Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:27bddd7b0cbb4f01b319821a797e89c1","is_oa":true,"landing_page_url":"https://doaj.org/article/27bddd7b0cbb4f01b319821a797e89c1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Image and Video Processing, Vol 2024, Iss 1, Pp 1-15 (2024)","raw_type":"article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/175469","is_oa":true,"landing_page_url":"https://hdl.handle.net/10356/175469","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1186/s13640-024-00620-9","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1186/s13640-024-00620-9","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13640-024-00620-9.pdf","source":{"id":"https://openalex.org/S153767265","display_name":"EURASIP Journal on Image and Video Processing","issn_l":"1687-5176","issn":["1687-5176","1687-5281"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Image and Video Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390705673.pdf","grobid_xml":"https://content.openalex.org/works/W4390705673.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2032699694","https://openalex.org/W2036167211","https://openalex.org/W2596142952","https://openalex.org/W2616247523","https://openalex.org/W2894906112","https://openalex.org/W2907475315","https://openalex.org/W2911495555","https://openalex.org/W2924476266","https://openalex.org/W2948171095","https://openalex.org/W2962805158","https://openalex.org/W2963281204","https://openalex.org/W2963283377","https://openalex.org/W2963448850","https://openalex.org/W2963845150","https://openalex.org/W2973136764","https://openalex.org/W2983166023","https://openalex.org/W3013629728","https://openalex.org/W3034648032","https://openalex.org/W3099486271","https://openalex.org/W3102564565","https://openalex.org/W3108975329","https://openalex.org/W3119399952","https://openalex.org/W3120387732","https://openalex.org/W3120940860","https://openalex.org/W3205534937","https://openalex.org/W3207833857","https://openalex.org/W4319163914","https://openalex.org/W6600195515"],"related_works":["https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W4281663961","https://openalex.org/W3208888551","https://openalex.org/W4313561566","https://openalex.org/W3208386644","https://openalex.org/W4220682630","https://openalex.org/W3181622257","https://openalex.org/W4389832810","https://openalex.org/W3133533225"],"abstract_inverted_index":{"Abstract":[0],"Multimodal":[1],"few-shot":[2,65],"learning":[3,66],"aims":[4],"to":[5,56,94,101,116,222],"exploit":[6],"complementary":[7],"information":[8],"inherent":[9],"in":[10,16,82,177],"multiple":[11],"modalities":[12],"for":[13,31,185,198],"vision":[14],"tasks":[15],"low":[17],"data":[18],"scenarios.":[19],"Most":[20],"of":[21,47,85,112,188,207],"the":[22,32,45,48,54,79,83,92,118,143,154,196,211,224],"current":[23],"research":[24],"focuses":[25],"on":[26,38],"a":[27,63,106,113,126,134,139,147,178],"suitable":[28],"embedding":[29,39,88],"space":[30],"various":[33],"modalities.":[34],"While":[35],"solutions":[36],"based":[37],"provide":[40],"state-of-the-art":[41],"results,":[42],"they":[43],"reduce":[44],"interpretability":[46,208],"model.":[49],"Separate":[50],"visualization":[51],"approaches":[52],"enable":[53],"models":[55],"become":[57],"more":[58],"transparent.":[59],"In":[60],"this":[61],"paper,":[62],"multimodal":[64,166],"framework":[67],"that":[68,130],"is":[69,72,75,123,131,183,213],"inherently":[70],"interpretable":[71],"presented.":[73],"This":[74,90],"achieved":[76],"by":[77,210,215],"using":[78],"textual":[80],"modality":[81],"form":[84],"attributes":[86,98,193],"without":[87],"them.":[89],"enables":[91],"model":[93,110,163,212],"directly":[95],"explain":[96],"which":[97,122,137],"caused":[99],"it":[100,219],"classify":[102],"an":[103],"image":[104,156],"into":[105],"particular":[107],"class.":[108],"The":[109,161,205],"consists":[111],"variational":[114],"autoencoder":[115],"learn":[117],"visual":[119],"latent":[120,128,144,159],"representation,":[121],"combined":[124],"with":[125],"semantic":[127,140],"representation":[129,145],"learnt":[132,221],"from":[133,157],"normal":[135],"autoencoder,":[136],"calculates":[138],"loss":[141],"between":[142],"and":[146,182,203],"binary":[148],"attribute":[149],"vector.":[150],"A":[151],"decoder":[152],"reconstructs":[153],"original":[155],"concatenated":[158],"vectors.":[160],"proposed":[162],"outperforms":[164],"other":[165],"methods":[167],"when":[168],"all":[169],"test":[170],"classes":[171,176],"are":[172,194,200],"used,":[173,195],"e.g.,":[174],"50":[175],"50-way":[179],"1-shot":[180],"setting,":[181],"comparable":[184],"lesser":[186],"number":[187],"ways.":[189],"Since":[190],"raw":[191],"text":[192],"datasets":[197],"evaluation":[199],"CUB,":[201],"SUN":[202],"AWA2.":[204],"effectiveness":[206],"provided":[209],"evaluated":[214],"analyzing":[216],"how":[217],"well":[218],"has":[220],"identify":[223],"attributes.":[225]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}