{"id":"https://openalex.org/W4417035264","doi":"https://doi.org/10.1109/wacv61042.2026.00307","title":"Learning Group Actions In Disentangled Latent Image Representations","display_name":"Learning Group Actions In Disentangled Latent Image Representations","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4417035264","doi":"https://doi.org/10.1109/wacv61042.2026.00307"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.04015","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5098790258","display_name":"Farhana Hossain Swarnali","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121829","display_name":"Genex Systems (United States)","ror":"https://ror.org/02mz0pc52","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121829"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Farhana Hossain Swarnali","raw_affiliation_strings":["Genuity Systems Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Genuity Systems Limited","institution_ids":["https://openalex.org/I4210121829"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357912","display_name":"Miaomiao Zhang","orcid":"https://orcid.org/0000-0003-0457-3335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miaomiao Zhang","raw_affiliation_strings":["Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004615608","display_name":"Tonmoy Hossain","orcid":"https://orcid.org/0000-0002-5808-6391"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tonmoy Hossain","raw_affiliation_strings":["Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01649559,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3140","last_page":"3149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.4553999900817871,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.4553999900817871,"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/T11448","display_name":"Face recognition and analysis","score":0.12030000239610672,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.10220000147819519,"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/prior-probability","display_name":"Prior probability","score":0.5929999947547913},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.550599992275238},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.4959999918937683},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.4894999861717224},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.48730000853538513},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43309998512268066},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.40380001068115234},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3903000056743622},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.3873000144958496}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.642799973487854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6133000254631042},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5929999947547913},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.550599992275238},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.4959999918937683},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.4894999861717224},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.48730000853538513},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43309998512268066},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4284000098705292},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.40380001068115234},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C11516046","wikidata":"https://www.wikidata.org/wiki/Q1055807","display_name":"Group representation","level":3,"score":0.329800009727478},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.3107999861240387},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2971000075340271},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2761000096797943},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.27379998564720154},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C171036898","wikidata":"https://www.wikidata.org/wiki/Q256355","display_name":"Equivariant map","level":2,"score":0.25859999656677246}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.04015","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.04015","pdf_url":"https://arxiv.org/pdf/2512.04015","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.04015","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.04015","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.04015","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.04015","pdf_url":"https://arxiv.org/pdf/2512.04015","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4417035264.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modeling":[0],"group":[1,29,75,96,142,175],"actions":[2,30,76,97,176],"on":[3,98,160],"latent":[4,60,99,121,139,172],"representations":[5,122],"enables":[6],"controllable":[7],"transformations":[8,20],"of":[9,59,187],"high-dimensional":[10,25],"image":[11,100,163],"data.":[12],"Prior":[13],"works":[14],"applying":[15],"group-theoretic":[16],"priors":[17],"or":[18],"modeling":[19],"typically":[21],"operate":[22,74],"in":[23,177],"the":[24,34,42,68,78,92,185,188],"data":[26],"space,":[27],"where":[28],"apply":[31],"uniformly":[32],"across":[33],"entire":[35],"input,":[36],"making":[37],"it":[38],"difficult":[39],"to":[40,70,118,168],"disentangle":[41],"subspace":[43],"that":[44,90,136],"varies":[45],"under":[46],"transformations.":[47],"While":[48],"latent-space":[49],"methods":[50],"offer":[51],"greater":[52],"flexibility,":[53],"they":[54],"still":[55],"require":[56],"manual":[57,107],"partitioning":[58],"variables":[61],"into":[62,123],"equivariant":[63],"and":[64,73,125,141],"invariant":[65,126],"subspaces,":[66],"limiting":[67],"ability":[69,167],"robustly":[71],"learn":[72,170],"within":[77,131],"representation":[79],"space.":[80],"To":[81],"address":[82],"this,":[83],"we":[84],"introduce":[85],"a":[86,132],"novel":[87],"end-to-end":[88],"framework":[89,135,146],"for":[91,174],"first":[93],"time":[94],"learns":[95,138],"manifolds,":[101],"automatically":[102,169],"discovering":[103],"transformation-relevant":[104],"structures":[105],"without":[106],"intervention.":[108],"Our":[109,191],"method":[110],"uses":[111],"learnable":[112],"binary":[113],"masks":[114],"with":[115,151],"straight-through":[116],"estimation":[117],"dynamically":[119],"partition":[120],"transformation-sensitive":[124],"components.":[127],"We":[128,156],"formulate":[129],"this":[130],"unified":[133],"optimization":[134],"jointly":[137],"disentanglement":[140],"transformation":[143],"mappings.":[144],"The":[145],"can":[147],"be":[148],"seamlessly":[149],"integrated":[150],"any":[152],"standard":[153],"encoder-decoder":[154],"architecture.":[155],"validate":[157],"our":[158],"approach":[159],"five":[161],"2D/3D":[162],"datasets,":[164],"demonstrating":[165],"its":[166],"disentangled":[171],"factors":[173],"diverse":[178],"data,":[179],"while":[180],"downstream":[181],"classification":[182],"tasks":[183],"confirm":[184],"effectiveness":[186],"learned":[189],"representations.":[190],"code":[192],"is":[193],"publicly":[194],"available":[195],"at":[196],"GitHub.":[197]},"counts_by_year":[],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-12-05T00:00:00"}