{"id":"https://openalex.org/W4385731829","doi":"https://doi.org/10.1109/tmm.2023.3304021","title":"MSViT: Training Multiscale Vision Transformers for Image Retrieval","display_name":"MSViT: Training Multiscale Vision Transformers for Image Retrieval","publication_year":2023,"publication_date":"2023-08-10","ids":{"openalex":"https://openalex.org/W4385731829","doi":"https://doi.org/10.1109/tmm.2023.3304021"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3304021","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3304021","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5100677774","display_name":"Xue Li","orcid":"https://orcid.org/0000-0002-8553-994X"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Li","raw_affiliation_strings":["School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0002-8553-994X","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020873493","display_name":"Jiong Yu","orcid":"https://orcid.org/0000-0002-9181-6720"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiong Yu","raw_affiliation_strings":["School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0002-9181-6720","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072497955","display_name":"Shaochen Jiang","orcid":"https://orcid.org/0000-0002-7896-1026"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaochen Jiang","raw_affiliation_strings":["School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0002-7896-1026","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043916192","display_name":"Hongchun Lu","orcid":"https://orcid.org/0000-0002-2087-3496"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongchun Lu","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2087-3496","affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100422864","display_name":"Ziyang Li","orcid":"https://orcid.org/0000-0003-2419-2548"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Li","raw_affiliation_strings":["School of Software, Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0003-2419-2548","affiliations":[{"raw_affiliation_string":"School of Software, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.3716,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.96019808,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"2809","last_page":"2823"},"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":0.9997000098228455,"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":0.9997000098228455,"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":0.9987999796867371,"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":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.8289524912834167},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6326377391815186},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6089981198310852},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.599152147769928},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5011687278747559},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.480782687664032},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.41564011573791504},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35554301738739014},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.33251315355300903},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3300352096557617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8289524912834167},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6326377391815186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6089981198310852},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.599152147769928},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5011687278747559},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.480782687664032},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.41564011573791504},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35554301738739014},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33251315355300903},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3300352096557617},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3304021","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3304021","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6874490511","display_name":null,"funder_award_id":"62262094","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1910300841","https://openalex.org/W1913628733","https://openalex.org/W1923967535","https://openalex.org/W1939575207","https://openalex.org/W2194775991","https://openalex.org/W2288290073","https://openalex.org/W2464915613","https://openalex.org/W2508837377","https://openalex.org/W2510911086","https://openalex.org/W2798834175","https://openalex.org/W2899885135","https://openalex.org/W2915217211","https://openalex.org/W2943563866","https://openalex.org/W2964280870","https://openalex.org/W2964349401","https://openalex.org/W2966218308","https://openalex.org/W2974497444","https://openalex.org/W2988396473","https://openalex.org/W3003608386","https://openalex.org/W3020188837","https://openalex.org/W3021619650","https://openalex.org/W3034239448","https://openalex.org/W3034315422","https://openalex.org/W3096609285","https://openalex.org/W3098087652","https://openalex.org/W3128099838","https://openalex.org/W3138516171","https://openalex.org/W3142124201","https://openalex.org/W3151130473","https://openalex.org/W3159460504","https://openalex.org/W3168649818","https://openalex.org/W3170874841","https://openalex.org/W3183541364","https://openalex.org/W3199828419","https://openalex.org/W3207602101","https://openalex.org/W4225654135","https://openalex.org/W4225947963","https://openalex.org/W4285216227","https://openalex.org/W4309368547","https://openalex.org/W4312693803","https://openalex.org/W4312725131","https://openalex.org/W4319452844","https://openalex.org/W4321608135","https://openalex.org/W4323897056","https://openalex.org/W6682778277","https://openalex.org/W6688152296","https://openalex.org/W6754813029","https://openalex.org/W6767696191","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6790570412","https://openalex.org/W6849846199"],"related_works":["https://openalex.org/W3177930984","https://openalex.org/W2052697133","https://openalex.org/W2076896210","https://openalex.org/W2384288472","https://openalex.org/W1539573266","https://openalex.org/W2093596879","https://openalex.org/W2376984068","https://openalex.org/W2201969175","https://openalex.org/W2017257332","https://openalex.org/W2747088704"],"abstract_inverted_index":{"The":[0,70,163],"recently":[1],"developed":[2],"vision":[3,22,51],"transformer":[4,85],"(ViT)":[5],"has":[6],"achieved":[7],"promising":[8],"results":[9,167],"on":[10,137,177,211],"image":[11,24,43,56,94,112,174,181],"retrieval":[12,25,57,95,175],"compared":[13],"to":[14,32,60,78,89,105,141,148],"convolutional":[15],"neural":[16],"networks.":[17],"However,":[18],"most":[19],"of":[20,39,64,72,84,93,134,165,214],"these":[21],"transformer-based":[23,52,99,173],"methods":[26,176],"use":[27],"the":[28,37,62,80,91,131,145,150,156,160,188,196,212],"original":[29],"ViT":[30],"model":[31],"extract":[33],"global":[34,65],"features,":[35],"ignoring":[36],"importance":[38],"local":[40,68],"features":[41,66,109],"for":[42,159],"retrieval.":[44],"In":[45],"this":[46,73],"work,":[47],"we":[48,118,154],"propose":[49],"a":[50,98,120],"multiscale":[53,121,198],"feature":[54,81,122,132,199],"fusion":[55,63,123,200],"method":[58,186],"(MSViT)":[59],"achieve":[61],"with":[67,114,168],"features.":[69],"challenge":[71],"research":[74],"work":[75],"is":[76,103],"how":[77],"learn":[79],"representation":[82],"ability":[83],"model,":[86],"so":[87],"as":[88],"improve":[90],"performance":[92,213],"model.":[96],"First,":[97],"two-branch":[100],"network":[101,151],"structure":[102],"proposed":[104],"obtain":[106],"different":[107,115,135],"scale":[108],"by":[110],"processing":[111],"patches":[113],"granularities.":[116],"Second,":[117],"present":[119],"strategy,":[124],"which":[125],"can":[126],"efficiently":[127],"and":[128,171,202],"effectively":[129],"fuse":[130],"information":[133,147],"sizes":[136],"two":[138],"branches.":[139],"Finally,":[140],"more":[142],"fully":[143],"utilize":[144],"label":[146],"supervise":[149],"training":[152],"process,":[153],"optimize":[155],"construction":[157],"rules":[158],"triplet":[161,204],"data.":[162],"comparison":[164],"experimental":[166],"ten":[169],"CNN-based":[170],"six":[172],"four":[178],"publicly":[179],"available":[180],"datasets":[182],"shows":[183],"that":[184,195],"our":[185],"outperforms":[187],"state-of-the-art":[189],"methods.":[190],"And":[191],"ablation":[192],"experiments":[193],"show":[194],"designed":[197],"strategy":[201],"improved":[203],"loss":[205],"function":[206],"have":[207],"an":[208],"implicit":[209],"improvement":[210],"MSViT.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":27},{"year":2024,"cited_by_count":8}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}