{"id":"https://openalex.org/W3033649369","doi":"https://doi.org/10.1109/tip.2021.3071688","title":"Learning Multi-Modal Nonlinear Embeddings: Performance Bounds and an Algorithm","display_name":"Learning Multi-Modal Nonlinear Embeddings: Performance Bounds and an Algorithm","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3033649369","doi":"https://doi.org/10.1109/tip.2021.3071688","mag":"3033649369","pmid":"https://pubmed.ncbi.nlm.nih.gov/33848248"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2021.3071688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2021.3071688","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":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.02330","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053289421","display_name":"Semih Kaya","orcid":"https://orcid.org/0000-0002-9305-706X"},"institutions":[{"id":"https://openalex.org/I201799495","display_name":"Middle East Technical University","ror":"https://ror.org/014weej12","country_code":"TR","type":"education","lineage":["https://openalex.org/I201799495"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Semih Kaya","raw_affiliation_strings":["METU, Ankara, Turkey","Department of Electrical and Electronics Engineering, METU, Ankara"],"affiliations":[{"raw_affiliation_string":"METU, Ankara, Turkey","institution_ids":[]},{"raw_affiliation_string":"Department of Electrical and Electronics Engineering, METU, Ankara","institution_ids":["https://openalex.org/I201799495"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023308958","display_name":"Elif Vural","orcid":"https://orcid.org/0000-0002-5491-2588"},"institutions":[{"id":"https://openalex.org/I201799495","display_name":"Middle East Technical University","ror":"https://ror.org/014weej12","country_code":"TR","type":"education","lineage":["https://openalex.org/I201799495"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Elif Vural","raw_affiliation_strings":["METU, Ankara, Turkey","Department of Electrical and Electronics Engineering, METU, Ankara"],"affiliations":[{"raw_affiliation_string":"METU, Ankara, Turkey","institution_ids":[]},{"raw_affiliation_string":"Department of Electrical and Electronics Engineering, METU, Ankara","institution_ids":["https://openalex.org/I201799495"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053289421"],"corresponding_institution_ids":["https://openalex.org/I201799495"],"apc_list":null,"apc_paid":null,"fwci":0.4845,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.63078569,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"30","issue":null,"first_page":"4384","last_page":"4394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991999864578247,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991999864578247,"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":0.9983999729156494,"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":0.996999979019165,"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/modal","display_name":"Modal","score":0.7630397081375122},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5964657068252563},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5820069313049316},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5370759963989258},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5334133505821228},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.49292469024658203},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.45586255192756653},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4249057173728943},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4223361909389496},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4196774661540985},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3545856177806854},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2960848808288574},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2556072473526001}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7630397081375122},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5964657068252563},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5820069313049316},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5370759963989258},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5334133505821228},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.49292469024658203},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.45586255192756653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4249057173728943},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4223361909389496},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4196774661540985},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3545856177806854},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2960848808288574},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2556072473526001},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tip.2021.3071688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2021.3071688","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:33848248","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33848248","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},{"id":"pmh:oai:arXiv.org:2006.02330","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.02330","pdf_url":"https://arxiv.org/pdf/2006.02330","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:https://open.metu.edu.tr:11511/90724","is_oa":false,"landing_page_url":"https://hdl.handle.net/11511/90724","pdf_url":null,"source":{"id":"https://openalex.org/S4306402495","display_name":"OpenMETU (Middle East Technical University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I201799495","host_organization_name":"Middle East Technical University","host_organization_lineage":["https://openalex.org/I201799495"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2006.02330","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.02330","pdf_url":"https://arxiv.org/pdf/2006.02330","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":78,"referenced_works":["https://openalex.org/W57680428","https://openalex.org/W118545087","https://openalex.org/W1123427201","https://openalex.org/W1202352811","https://openalex.org/W1560143607","https://openalex.org/W1592111270","https://openalex.org/W1670132599","https://openalex.org/W1700224340","https://openalex.org/W1880262756","https://openalex.org/W1953764758","https://openalex.org/W1964073652","https://openalex.org/W1979840843","https://openalex.org/W2031823405","https://openalex.org/W2035299679","https://openalex.org/W2037227137","https://openalex.org/W2037603696","https://openalex.org/W2048679005","https://openalex.org/W2070753207","https://openalex.org/W2071207147","https://openalex.org/W2106277773","https://openalex.org/W2111700528","https://openalex.org/W2133026717","https://openalex.org/W2140076625","https://openalex.org/W2143697476","https://openalex.org/W2143790202","https://openalex.org/W2154462399","https://openalex.org/W2155797815","https://openalex.org/W2166782149","https://openalex.org/W2167090521","https://openalex.org/W2184188583","https://openalex.org/W2186094539","https://openalex.org/W2186500555","https://openalex.org/W2202025056","https://openalex.org/W2210322478","https://openalex.org/W2211092169","https://openalex.org/W2326180695","https://openalex.org/W2343933232","https://openalex.org/W2397674542","https://openalex.org/W2414522539","https://openalex.org/W2470996195","https://openalex.org/W2474574787","https://openalex.org/W2476034201","https://openalex.org/W2541562638","https://openalex.org/W2588822028","https://openalex.org/W2605146283","https://openalex.org/W2725249286","https://openalex.org/W2752235486","https://openalex.org/W2753064086","https://openalex.org/W2800761708","https://openalex.org/W2912990735","https://openalex.org/W2962967183","https://openalex.org/W2963051525","https://openalex.org/W2963560814","https://openalex.org/W2963743271","https://openalex.org/W2963991565","https://openalex.org/W2968891686","https://openalex.org/W2970877864","https://openalex.org/W2971035971","https://openalex.org/W2982395388","https://openalex.org/W2986784689","https://openalex.org/W3033649369","https://openalex.org/W4231510805","https://openalex.org/W6602211964","https://openalex.org/W6602375370","https://openalex.org/W6604797567","https://openalex.org/W6636883489","https://openalex.org/W6639619044","https://openalex.org/W6679546315","https://openalex.org/W6680860788","https://openalex.org/W6683120131","https://openalex.org/W6686207219","https://openalex.org/W6695508029","https://openalex.org/W6712554547","https://openalex.org/W6720414955","https://openalex.org/W6721087566","https://openalex.org/W6736441558","https://openalex.org/W6767290254","https://openalex.org/W6778881243"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W2413243053","https://openalex.org/W410723623","https://openalex.org/W2015341305","https://openalex.org/W2035068594","https://openalex.org/W4225593417","https://openalex.org/W2573498121","https://openalex.org/W3022298670","https://openalex.org/W3160494304","https://openalex.org/W2167883292"],"abstract_inverted_index":{"While":[0],"many":[1],"approaches":[2],"exist":[3],"in":[4,14,46,58,139],"the":[5,17,64,67,71,74,82,106,109,116,120,133],"literature":[6],"to":[7,23,73,124],"learn":[8],"low-dimensional":[9],"representations":[10],"for":[11,55],"data":[12,26,76],"collections":[13],"multiple":[15],"modalities,":[16],"generalizability":[18],"of":[19,41,66,108,119],"multi-modal":[20,43,59,93,126,140],"nonlinear":[21,44,94],"embeddings":[22,45,107],"previously":[24],"unseen":[25],"is":[27,78,99],"a":[28,38,47,92],"rather":[29],"overlooked":[30],"subject.":[31],"In":[32],"this":[33],"work,":[34],"we":[35],"first":[36],"present":[37],"theoretical":[39,103],"analysis":[40],"learning":[42,96,129],"supervised":[48],"setting.":[49],"Our":[50],"performance":[51,138],"bounds":[52],"indicate":[53],"that":[54,98,132],"successful":[56],"generalization":[57],"classification":[60,142],"and":[61,85,127,143],"retrieval":[62,146],"problems,":[63],"regularity":[65,118],"interpolation":[68],"functions":[69],"extending":[70],"embedding":[72],"whole":[75],"space":[77],"as":[79,81],"important":[80],"between-class":[83],"separation":[84],"cross-modal":[86,144],"alignment":[87],"criteria.":[88],"We":[89],"then":[90],"propose":[91],"representation":[95],"algorithm":[97],"motivated":[100],"by":[101],"these":[102],"findings,":[104],"where":[105],"training":[110],"samples":[111],"are":[112],"optimized":[113],"jointly":[114],"with":[115],"Lipschitz":[117],"interpolators.":[121],"Experimental":[122],"comparison":[123],"recent":[125],"single-modal":[128],"algorithms":[130],"suggests":[131],"proposed":[134],"method":[135],"yields":[136],"promising":[137],"image":[141],"image-text":[145],"applications.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2021-04-26T00:00:00"}