{"id":"https://openalex.org/W7123346706","doi":"https://doi.org/10.1109/tip.2025.3649364","title":"Revisiting Fine-Grained Image Analysis by Semantic-Part Alignment","display_name":"Revisiting Fine-Grained Image Analysis by Semantic-Part Alignment","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7123346706","doi":"https://doi.org/10.1109/tip.2025.3649364","pmid":"https://pubmed.ncbi.nlm.nih.gov/41525540"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2025.3649364","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3649364","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5035415308","display_name":"Qi Bi","orcid":"https://orcid.org/0000-0002-1047-4790"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Qi Bi","raw_affiliation_strings":["Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068565464","display_name":"Jingjun Yi","orcid":"https://orcid.org/0000-0002-4249-3021"},"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/I4210118728","display_name":"State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing","ror":"https://ror.org/02bpap860","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118728"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjun Yi","raw_affiliation_strings":["State Key Laboratory of LIESMARS, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of LIESMARS, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I4210118728","https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122905797","display_name":"Haolan Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Haolan Zhan","raw_affiliation_strings":["Faculty of Information Technology, Monash University, Melbourne, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Monash University, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Ji","orcid":"https://orcid.org/0000-0003-4059-5902"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Ji","raw_affiliation_strings":["School of Medicine, Yale University, New Haven, CT, USA"],"affiliations":[{"raw_affiliation_string":"School of Medicine, Yale University, New Haven, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"last","author":{"id":null,"display_name":"Gui-Song Xia","orcid":"https://orcid.org/0000-0001-7660-6090"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gui-Song Xia","raw_affiliation_strings":["School of Artificial Intelligence, the National Engineering Research Center for Multimedia Software, the School of Computer Science, and the State Key Laboratory of LIESMARS, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, the National Engineering Research Center for Multimedia Software, the School of Computer Science, and the State Key Laboratory of LIESMARS, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5035415308"],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0860131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"670","last_page":"684"},"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":0.4361000061035156,"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":0.4361000061035156,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.19519999623298645,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.13009999692440033,"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/discriminative-model","display_name":"Discriminative model","score":0.7633000016212463},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.7314000129699707},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7124999761581421},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6184999942779541},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.592199981212616},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5745000243186951},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5489000082015991},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48500001430511475},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4438000023365021},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4350999891757965}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7633000016212463},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.7314000129699707},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7124999761581421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6625999808311462},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.637499988079071},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6184999942779541},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.592199981212616},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5745000243186951},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5489000082015991},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48500001430511475},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4438000023365021},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4350999891757965},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3637999892234802},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.3630000054836273},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.322299987077713},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.3133000135421753},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.31290000677108765},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2985000014305115},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.29010000824928284},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27090001106262207},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2025.3649364","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3649364","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:41525540","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41525540","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":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7528174519538879}],"awards":[{"id":"https://openalex.org/G304847476","display_name":null,"funder_award_id":"No.62325111","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3965009956","display_name":null,"funder_award_id":"U22B2011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6734123255","display_name":null,"funder_award_id":"No.U22B2011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7875021329","display_name":null,"funder_award_id":"62325111","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":99,"referenced_works":["https://openalex.org/W1954152232","https://openalex.org/W2138011018","https://openalex.org/W2194775991","https://openalex.org/W2204750386","https://openalex.org/W2289708887","https://openalex.org/W2432402544","https://openalex.org/W2519904008","https://openalex.org/W2563764042","https://openalex.org/W2596603442","https://openalex.org/W2798365843","https://openalex.org/W2891951760","https://openalex.org/W2957105406","https://openalex.org/W2961018736","https://openalex.org/W2962858109","https://openalex.org/W2963047834","https://openalex.org/W2963393555","https://openalex.org/W2963407932","https://openalex.org/W2963446712","https://openalex.org/W2963805953","https://openalex.org/W2963842104","https://openalex.org/W2965318645","https://openalex.org/W2967515867","https://openalex.org/W2969810168","https://openalex.org/W2986821660","https://openalex.org/W2997426000","https://openalex.org/W2997987796","https://openalex.org/W2998619563","https://openalex.org/W2998776895","https://openalex.org/W3009073662","https://openalex.org/W3014509175","https://openalex.org/W3035367622","https://openalex.org/W3035539956","https://openalex.org/W3035645942","https://openalex.org/W3092740872","https://openalex.org/W3108870912","https://openalex.org/W3115484111","https://openalex.org/W3130788242","https://openalex.org/W3138516171","https://openalex.org/W3139434170","https://openalex.org/W3139438386","https://openalex.org/W3143016713","https://openalex.org/W3150864706","https://openalex.org/W3167101089","https://openalex.org/W3167308647","https://openalex.org/W3172917901","https://openalex.org/W3173635859","https://openalex.org/W3194557739","https://openalex.org/W3195399086","https://openalex.org/W3202750592","https://openalex.org/W3206734547","https://openalex.org/W3210946531","https://openalex.org/W3212813052","https://openalex.org/W3213639431","https://openalex.org/W4214736485","https://openalex.org/W4281723345","https://openalex.org/W4304083944","https://openalex.org/W4307091871","https://openalex.org/W4312235460","https://openalex.org/W4312236429","https://openalex.org/W4312361652","https://openalex.org/W4312622050","https://openalex.org/W4312700302","https://openalex.org/W4312706437","https://openalex.org/W4312936309","https://openalex.org/W4313188957","https://openalex.org/W4313886956","https://openalex.org/W4382460786","https://openalex.org/W4383503856","https://openalex.org/W4383899699","https://openalex.org/W4385338545","https://openalex.org/W4386057726","https://openalex.org/W4386065693","https://openalex.org/W4386066416","https://openalex.org/W4386075994","https://openalex.org/W4386076234","https://openalex.org/W4386076618","https://openalex.org/W4386138397","https://openalex.org/W4390661786","https://openalex.org/W4390871942","https://openalex.org/W4390874481","https://openalex.org/W4392208008","https://openalex.org/W4393150367","https://openalex.org/W4393154594","https://openalex.org/W4393252676","https://openalex.org/W4398764933","https://openalex.org/W4399849389","https://openalex.org/W4402703085","https://openalex.org/W4402753418","https://openalex.org/W4402952238","https://openalex.org/W4403790959","https://openalex.org/W4403791667","https://openalex.org/W4405747181","https://openalex.org/W4406089980","https://openalex.org/W4407376583","https://openalex.org/W4409346528","https://openalex.org/W4410342729","https://openalex.org/W4413144328","https://openalex.org/W4415795625","https://openalex.org/W4415796426"],"related_works":[],"abstract_inverted_index":{"Fine-grained":[0],"image":[1,138,197],"analysis":[2,198],"is":[3,36,68,82,90,153,172],"widely":[4],"recognized":[5],"as":[6,39],"highly":[7],"challenging,":[8],"since":[9],"distinguishing":[10],"individual":[11],"differences":[12],"within":[13],"a":[14,75,144],"certain":[15],"category,":[16],"species,":[17],"or":[18],"type":[19],"often":[20],"depends":[21],"on":[22,194],"tiny,":[23],"subtle":[24,33,66],"patterns.":[25],"However,":[26],"learning":[27,80],"fine-grained":[28,62,101,107,141,160,196],"semantic":[29,161],"categories":[30],"from":[31],"these":[32,65],"part":[34,98,135,166],"patterns":[35,48,67],"inherently":[37],"fragile,":[38],"they":[40],"can":[41,190],"easily":[42],"be":[43],"overwhelmed":[44],"by":[45],"the":[46,51,58,61,69,94,100,106,140,148,157,164,169,178,187],"dominant":[47],"resting":[49],"in":[50,84,136,143],"coarse-category":[52],"information.":[53],"Therefore,":[54],"how":[55],"to":[56,91,99,155,177],"enhance":[57,156],"relation":[59,158],"between":[60,159],"semantics":[63,142],"and":[64,103,125,163,175,182],"key.":[70],"To":[71],"push":[72],"this":[73,85],"frontier,":[74],"novel":[76],"semantic-part":[77,120,122,127,131,150],"alignment":[78],"(SPA)":[79],"scheme":[81],"proposed":[83,170,188],"paper.":[86],"Its":[87],"general":[88],"idea":[89],"firstly":[92],"measure":[93],"relevance":[95],"of":[96,114],"each":[97,134],"semantics,":[102],"then":[104],"regularize":[105],"visual":[108],"representation":[109],"learning.":[110],"Specifically,":[111],"it":[112],"consists":[113],"three":[115],"key":[116],"components,":[117],"namely,":[118],"joint":[119,130],"modeling,":[121,124],"set":[123],"optimal":[126,149],"transport.":[128],"The":[129],"modeling":[132],"associates":[133],"an":[137],"with":[139],"latent":[145,179],"space.":[146],"Then,":[147],"transport":[151],"component":[152],"devised":[154],"embeddings":[162],"discriminative":[165],"embeddings.":[167],"Notably,":[168],"SPA":[171],"plug-in-and-play,":[173],"easy-to-implement,":[174],"insensitive":[176],"embedding":[180],"dimension":[181],"loss":[183],"weight.":[184],"Experiments":[185],"show":[186],"method":[189],"substantially":[191],"boost":[192],"performance":[193],"multiple":[195],"tasks":[199],"across":[200],"various":[201],"baselines.":[202]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-14T00:00:00"}