{"id":"https://openalex.org/W4416166986","doi":"https://doi.org/10.3390/jimaging11110410","title":"TASA: Text-Anchored State\u2013Space Alignment for Long-Tailed Image Classification","display_name":"TASA: Text-Anchored State\u2013Space Alignment for Long-Tailed Image Classification","publication_year":2025,"publication_date":"2025-11-13","ids":{"openalex":"https://openalex.org/W4416166986","doi":"https://doi.org/10.3390/jimaging11110410","pmid":"https://pubmed.ncbi.nlm.nih.gov/41295127"},"language":"en","primary_location":{"id":"doi:10.3390/jimaging11110410","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging11110410","pdf_url":"https://www.mdpi.com/2313-433X/11/11/410/pdf?version=1762998378","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2313-433X/11/11/410/pdf?version=1762998378","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Long Li","orcid":"https://orcid.org/0009-0007-1507-8504"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Li","raw_affiliation_strings":["School of Information Engineering, Chang\u2019an University, Xi\u2019an 710064, China","School of Information Engineering, Chang'an University, Xi'an 710064, China"],"raw_orcid":"https://orcid.org/0009-0007-1507-8504","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang\u2019an University, Xi\u2019an 710064, China","institution_ids":["https://openalex.org/I25355098"]},{"raw_affiliation_string":"School of Information Engineering, Chang'an University, Xi'an 710064, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tinglei Jia","orcid":"https://orcid.org/0009-0008-5723-6184"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tinglei Jia","raw_affiliation_strings":["School of Information Engineering, Chang\u2019an University, Xi\u2019an 710064, China","School of Information Engineering, Chang'an University, Xi'an 710064, China"],"raw_orcid":"https://orcid.org/0009-0008-5723-6184","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang\u2019an University, Xi\u2019an 710064, China","institution_ids":["https://openalex.org/I25355098"]},{"raw_affiliation_string":"School of Information Engineering, Chang'an University, Xi'an 710064, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110477539","display_name":"Hongsheng Yue","orcid":"https://orcid.org/0009-0007-0570-3134"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaizhi Yue","raw_affiliation_strings":["School of Information Engineering, Chang\u2019an University, Xi\u2019an 710064, China","School of Information Engineering, Chang'an University, Xi'an 710064, China"],"raw_orcid":"https://orcid.org/0009-0007-0570-3134","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang\u2019an University, Xi\u2019an 710064, China","institution_ids":["https://openalex.org/I25355098"]},{"raw_affiliation_string":"School of Information Engineering, Chang'an University, Xi'an 710064, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104201124","display_name":"Huize Cheng","orcid":"https://orcid.org/0009-0009-3396-8468"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huize Cheng","raw_affiliation_strings":["School of Information Engineering, Chang\u2019an University, Xi\u2019an 710064, China","School of Information Engineering, Chang'an University, Xi'an 710064, China"],"raw_orcid":"https://orcid.org/0009-0009-3396-8468","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang\u2019an University, Xi\u2019an 710064, China","institution_ids":["https://openalex.org/I25355098"]},{"raw_affiliation_string":"School of Information Engineering, Chang'an University, Xi'an 710064, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112754056","display_name":"Yongfeng Bu","orcid":"https://orcid.org/0009-0006-8898-4308"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongfeng Bu","raw_affiliation_strings":["School of Information Engineering, Chang\u2019an University, Xi\u2019an 710064, China","School of Information Engineering, Chang'an University, Xi'an 710064, China"],"raw_orcid":"https://orcid.org/0009-0006-8898-4308","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang\u2019an University, Xi\u2019an 710064, China","institution_ids":["https://openalex.org/I25355098"]},{"raw_affiliation_string":"School of Information Engineering, Chang'an University, Xi'an 710064, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100751310","display_name":"Zhaoyang Zhang","orcid":"https://orcid.org/0000-0003-2287-2486"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhaoyang Zhang","raw_affiliation_strings":["School of Information Engineering, Chang\u2019an University, Xi\u2019an 710064, China","School of Information Engineering, Chang'an University, Xi'an 710064, China"],"raw_orcid":"https://orcid.org/0000-0003-2287-2486","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang\u2019an University, Xi\u2019an 710064, China","institution_ids":["https://openalex.org/I25355098"]},{"raw_affiliation_string":"School of Information Engineering, Chang'an University, Xi'an 710064, China","institution_ids":["https://openalex.org/I25355098"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100751310"],"corresponding_institution_ids":["https://openalex.org/I25355098"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":1.9057,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90174883,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"11","issue":"11","first_page":"410","last_page":"410"},"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":0.5812000036239624,"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":0.5812000036239624,"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":0.11860000342130661,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.05939999967813492,"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/fusion","display_name":"Fusion","score":0.6527000069618225},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5845000147819519},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5575000047683716},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5429999828338623},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5044000148773193},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4821000099182129},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4392000138759613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7796000242233276},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.6527000069618225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.619700014591217},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5845000147819519},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5575000047683716},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5429999828338623},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5044000148773193},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4821000099182129},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4392000138759613},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.36880001425743103},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33719998598098755},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30880001187324524},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.262800008058548}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/jimaging11110410","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging11110410","pdf_url":"https://www.mdpi.com/2313-433X/11/11/410/pdf?version=1762998378","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},{"id":"pmid:41295127","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41295127","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of imaging","raw_type":null},{"id":"pmh:oai:doaj.org/article:cd1c922f41bb440dbddb791083e4aee3","is_oa":true,"landing_page_url":"https://doaj.org/article/cd1c922f41bb440dbddb791083e4aee3","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":"Journal of Imaging, Vol 11, Iss 11, p 410 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/jimaging11110410","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging11110410","pdf_url":"https://www.mdpi.com/2313-433X/11/11/410/pdf?version=1762998378","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321525","display_name":"Chang'an University","ror":"https://ror.org/05mxya461"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416166986.pdf","grobid_xml":"https://content.openalex.org/works/W4416166986.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W2185175083","https://openalex.org/W2949736877","https://openalex.org/W2962933664","https://openalex.org/W2963351448","https://openalex.org/W2963691377","https://openalex.org/W3034601242","https://openalex.org/W3128945844","https://openalex.org/W3175613352","https://openalex.org/W3176474016","https://openalex.org/W3177230409","https://openalex.org/W3198377975","https://openalex.org/W4200301265","https://openalex.org/W4214640945","https://openalex.org/W4281492582","https://openalex.org/W4312244159","https://openalex.org/W4366352743","https://openalex.org/W4385212332","https://openalex.org/W4386065868","https://openalex.org/W4386071707","https://openalex.org/W4386076553","https://openalex.org/W4386083102","https://openalex.org/W4390872508","https://openalex.org/W4391537734","https://openalex.org/W4391547487","https://openalex.org/W4392122189","https://openalex.org/W4402776071","https://openalex.org/W4403562063","https://openalex.org/W4404690880","https://openalex.org/W4407950371","https://openalex.org/W4408514889","https://openalex.org/W4411446408","https://openalex.org/W4413147026","https://openalex.org/W4415593370","https://openalex.org/W4415797365","https://openalex.org/W4415798326"],"related_works":[],"abstract_inverted_index":{"Long-tailed":[0],"image":[1,87],"classification":[2,116],"remains":[3],"challenging":[4],"for":[5,115,175],"vision-language":[6],"models.":[7],"Head":[8],"classes":[9,14],"dominate":[10],"training":[11,73],"while":[12,151],"tail":[13],"are":[15],"underrepresented":[16],"and":[17,19,41,68,88,94,130,138,153,160],"noisy,":[18],"short":[20],"prompts":[21],"with":[22,62,104,112,172],"weak":[23],"text":[24,53,74,89],"supervision":[25,40],"further":[26],"amplify":[27],"head":[28],"bias.":[29],"This":[30],"paper":[31],"presents":[32],"TASA,":[33],"an":[34],"end-to-end":[35],"framework":[36],"that":[37,144],"stabilizes":[38],"textual":[39],"enhances":[42],"cross-modal":[43],"fusion.":[44],"A":[45],"Semantic":[46],"Distribution":[47],"Modulation":[48],"(SDM)":[49],"module":[50,80],"constructs":[51],"class-specific":[52],"prototypes":[54,114,171],"by":[55],"cosine-weighted":[56],"fusion":[57,97,174],"of":[58,168],"multiple":[59],"LLM-generated":[60],"descriptions":[61],"a":[63,99,105],"canonical":[64],"template,":[65],"providing":[66],"stable":[67],"diverse":[69],"semantic":[70],"anchors":[71],"without":[72,117],"parameters.":[75],"Dual-Space":[76],"Cross-Modal":[77],"Fusion":[78],"(DCF)":[79],"incorporates":[81],"selective-scan":[82],"state-space":[83,173],"blocks":[84],"into":[85],"both":[86],"branches,":[90],"enabling":[91],"bidirectional":[92],"conditioning":[93],"efficient":[95],"feature":[96],"through":[98],"lightweight":[100],"multilayer":[101],"perceptron.":[102],"Together":[103],"margin-aware":[106],"alignment":[107],"loss,":[108],"TASA":[109],"aligns":[110],"images":[111],"class":[113],"requiring":[118],"paired":[119],"image-text":[120],"data":[121],"or":[122],"per-class":[123],"prompt":[124],"tuning.":[125],"Experiments":[126],"on":[127],"CIFAR-10/100-LT,":[128],"ImageNet-LT,":[129],"Places-LT":[131],"demonstrate":[132],"consistent":[133],"improvements":[134],"across":[135],"many-,":[136],"medium-,":[137],"few-shot":[139],"groups.":[140],"Ablation":[141],"studies":[142],"confirm":[143],"DCF":[145,154],"yields":[146],"the":[147,157,166],"largest":[148],"single-module":[149],"gain,":[150],"SDM":[152],"combined":[155],"provide":[156],"most":[158],"robust":[159],"balanced":[161],"performance.":[162],"These":[163],"results":[164],"highlight":[165],"effectiveness":[167],"integrating":[169],"text-driven":[170],"long-tailed":[176],"classification.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-11-13T00:00:00"}
