{"id":"https://openalex.org/W3130089801","doi":"https://doi.org/10.1109/access.2021.3061765","title":"Pairwise Context Similarity for Image Retrieval System Using Variational Auto-Encoder","display_name":"Pairwise Context Similarity for Image Retrieval System Using Variational Auto-Encoder","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3130089801","doi":"https://doi.org/10.1109/access.2021.3061765","mag":"3130089801"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3061765","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3061765","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09361679.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09361679.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044469790","display_name":"Hyeongu Yun","orcid":"https://orcid.org/0000-0002-1506-6200"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeongu Yun","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-1506-6200","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101964120","display_name":"Yongil Kim","orcid":"https://orcid.org/0000-0003-0541-8986"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yongil Kim","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082023846","display_name":"Taegwan Kang","orcid":"https://orcid.org/0000-0002-9171-357X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taegwan Kang","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-9171-357X","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077832834","display_name":"Kyomin Jung","orcid":"https://orcid.org/0000-0003-2547-7051"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyomin Jung","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0942,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.33460625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"9","issue":null,"first_page":"34067","last_page":"34077"},"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":1.0,"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":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991000294685364,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9987000226974487,"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/pairwise-comparison","display_name":"Pairwise comparison","score":0.8609514832496643},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7459919452667236},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.7278679609298706},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6728907227516174},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6310799717903137},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6198376417160034},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5369515419006348},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5089592933654785},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5078755021095276},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4911353290081024},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4416102170944214},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.42511945962905884},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3440440893173218},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2740080654621124},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.09219571948051453}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.8609514832496643},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7459919452667236},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7278679609298706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6728907227516174},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6310799717903137},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6198376417160034},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5369515419006348},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5089592933654785},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5078755021095276},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4911353290081024},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4416102170944214},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.42511945962905884},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3440440893173218},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2740080654621124},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09219571948051453},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3061765","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3061765","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09361679.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:26813ef0398d4d769b8719a63ad4e5f0","is_oa":true,"landing_page_url":"https://doaj.org/article/26813ef0398d4d769b8719a63ad4e5f0","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":"IEEE Access, Vol 9, Pp 34067-34077 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3061765","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3061765","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09361679.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4050664357","display_name":null,"funder_award_id":"IO201208-07852-01","funder_id":"https://openalex.org/F4320332195","funder_display_name":"Samsung"}],"funders":[{"id":"https://openalex.org/F4320321292","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3130089801.pdf","grobid_xml":"https://content.openalex.org/works/W3130089801.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W1230023165","https://openalex.org/W1546243588","https://openalex.org/W1870428314","https://openalex.org/W1910300841","https://openalex.org/W1939575207","https://openalex.org/W1959608418","https://openalex.org/W1982193706","https://openalex.org/W1992371516","https://openalex.org/W1998803396","https://openalex.org/W2007972815","https://openalex.org/W2038735287","https://openalex.org/W2050405843","https://openalex.org/W2074668987","https://openalex.org/W2121713321","https://openalex.org/W2142431032","https://openalex.org/W2155803963","https://openalex.org/W2162721653","https://openalex.org/W2163605009","https://openalex.org/W2164338181","https://openalex.org/W2194775991","https://openalex.org/W2221852422","https://openalex.org/W2251864938","https://openalex.org/W2259768202","https://openalex.org/W2293597654","https://openalex.org/W2293824885","https://openalex.org/W2508837377","https://openalex.org/W2562322388","https://openalex.org/W2727724078","https://openalex.org/W2741246388","https://openalex.org/W2766596763","https://openalex.org/W2798834175","https://openalex.org/W2798956329","https://openalex.org/W2890960987","https://openalex.org/W2900790473","https://openalex.org/W2913932916","https://openalex.org/W2915217211","https://openalex.org/W2964011399","https://openalex.org/W2964158883","https://openalex.org/W2964280870","https://openalex.org/W2996769726","https://openalex.org/W3034239448","https://openalex.org/W3035732386","https://openalex.org/W3089135124","https://openalex.org/W3106264379","https://openalex.org/W3118608800","https://openalex.org/W4299512017","https://openalex.org/W6639283537","https://openalex.org/W6640963894","https://openalex.org/W6648560114","https://openalex.org/W6678291700","https://openalex.org/W6682859755","https://openalex.org/W6684181414","https://openalex.org/W6684191040","https://openalex.org/W6688844344","https://openalex.org/W6691474080","https://openalex.org/W6697060382","https://openalex.org/W6697214482","https://openalex.org/W6725199262","https://openalex.org/W6730864085","https://openalex.org/W6745792544","https://openalex.org/W6754813029","https://openalex.org/W6774835893"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4289763776","https://openalex.org/W2810330923"],"abstract_inverted_index":{"Deep-learning-to-hash":[0],"models":[1,40,135],"have":[2],"recently":[3],"achieved":[4,164],"several":[5],"breakthroughs":[6],"enabling":[7],"a":[8,36,86,107,192],"fast":[9],"and":[10,208],"efficient":[11],"image":[12,169],"retrieval":[13,151,166,170],"system.":[14],"As":[15],"supervision":[16,78],"for":[17,79,133,168],"deep-learning-to-hash":[18,81,134],"models,":[19],"pairwise":[20,43,54,73,88,97,145],"label":[21,44,55,74,122,146],"similarity":[22,45,56,75,90,99,147],"which":[23,110],"considers":[24],"two":[25,67],"images":[26,52],"to":[27,91,178,205],"be":[28,139],"identical":[29,34],"if":[30],"their":[31],"labels":[32],"are":[33],"plays":[35],"crucial":[37],"role.":[38],"However,":[39],"using":[41,71,144],"only":[42,77],"cannot":[46],"incorporate":[47],"rich":[48],"contextual":[49],"information":[50],"in":[51,113],"because":[53],"solely":[57],"depends":[58],"on":[59,102,156],"labels.":[60],"In":[61,153],"this":[62],"paper,":[63],"we":[64,84,125,183],"initially":[65],"address":[66],"major":[68],"limitations":[69],"of":[70,106,129],"the":[72,80,103,127,150,179,210],"as":[76,191],"model.":[82],"Then,":[83],"propose":[85,126],"novel":[87],"context":[89,98],"alleviate":[92],"those":[93],"limitations.":[94,181],"The":[95],"proposed":[96,162,188],"is":[100,111],"computed":[101],"latent":[104],"space":[105],"Variational":[108],"Auto-Encoder":[109],"trained":[112],"an":[114,130],"unsupervised":[115],"fashion":[116],"that":[117,136,186,199],"does":[118],"not":[119],"utilize":[120],"any":[121],"information.":[123],"Moreover":[124],"strategy":[128],"auxiliary":[131],"loss":[132,201],"can":[137],"easily":[138],"combined":[140],"with":[141,176],"previous":[142],"losses":[143],"without":[148],"deteriorating":[149],"quality.":[152],"our":[154,161,187,200],"experiments":[155],"three":[157],"standard":[158],"benchmark":[159],"datasets,":[160],"method":[163,189],"high":[165],"quality":[167],"tasks":[171],"while":[172],"also":[173],"showing":[174],"advantages":[175],"regard":[177],"addressed":[180],"Also,":[182],"empirically":[184],"prove":[185],"acts":[190],"proper":[193],"regularization":[194],"term":[195,202],"during":[196],"training":[197,211],"so":[198],"therefore":[203],"helps":[204],"mitigate":[206],"overfitting":[207],"stabilizes":[209],"curves.":[212]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}