{"id":"https://openalex.org/W4378697123","doi":"https://doi.org/10.1109/tmm.2023.3280734","title":"Towards Fast and Accurate Image-Text Retrieval With Self-Supervised Fine-Grained Alignment","display_name":"Towards Fast and Accurate Image-Text Retrieval With Self-Supervised Fine-Grained Alignment","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4378697123","doi":"https://doi.org/10.1109/tmm.2023.3280734"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3280734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3280734","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.14009","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103275773","display_name":"Jiamin Zhuang","orcid":"https://orcid.org/0000-0002-1598-0764"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiamin Zhuang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1598-0764","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101672021","display_name":"Jing Yu","orcid":"https://orcid.org/0000-0002-3966-511X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Yu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3966-511X","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103136578","display_name":"Yang Ding","orcid":"https://orcid.org/0009-0004-0375-995X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Ding","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069741268","display_name":"Xiangyan Qu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyan Qu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3658-8099","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100684459","display_name":"Yue Hu","orcid":"https://orcid.org/0000-0002-4416-3974"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Hu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4416-3974","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1493,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.88525511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"1361","last_page":"1372"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/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":0.9986000061035156,"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":0.8321722149848938},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6487376093864441},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5027337074279785},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4685704708099365},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4321850836277008},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.42649561166763306},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3885357975959778},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3705698847770691}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8321722149848938},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6487376093864441},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5027337074279785},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4685704708099365},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4321850836277008},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.42649561166763306},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3885357975959778},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3705698847770691}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2023.3280734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3280734","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"},{"id":"pmh:oai:arXiv.org:2308.14009","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.14009","pdf_url":"https://arxiv.org/pdf/2308.14009","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.14009","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.14009","pdf_url":"https://arxiv.org/pdf/2308.14009","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":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G1491006677","display_name":null,"funder_award_id":"62006222","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":49,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W2185175083","https://openalex.org/W2187089797","https://openalex.org/W2552579943","https://openalex.org/W2765440071","https://openalex.org/W2798991696","https://openalex.org/W2883725317","https://openalex.org/W2896457183","https://openalex.org/W2952524542","https://openalex.org/W2962964995","https://openalex.org/W2963040148","https://openalex.org/W2965848243","https://openalex.org/W2979579363","https://openalex.org/W2981586349","https://openalex.org/W2988823324","https://openalex.org/W2994818707","https://openalex.org/W2997525715","https://openalex.org/W3010277541","https://openalex.org/W3035454331","https://openalex.org/W3035524453","https://openalex.org/W3035552787","https://openalex.org/W3035605030","https://openalex.org/W3090449556","https://openalex.org/W3092820619","https://openalex.org/W3100923070","https://openalex.org/W3139017368","https://openalex.org/W3155230099","https://openalex.org/W3166304536","https://openalex.org/W3168822201","https://openalex.org/W3171668871","https://openalex.org/W3177155667","https://openalex.org/W3190055600","https://openalex.org/W3212100893","https://openalex.org/W6678470764","https://openalex.org/W6685183736","https://openalex.org/W6726873649","https://openalex.org/W6739901393","https://openalex.org/W6747225742","https://openalex.org/W6754278344","https://openalex.org/W6763416564","https://openalex.org/W6774314701","https://openalex.org/W6779997284","https://openalex.org/W6790019176","https://openalex.org/W6790850890","https://openalex.org/W6791353385","https://openalex.org/W6797371478"],"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/W2747088704","https://openalex.org/W2017257332"],"abstract_inverted_index":{"Image-text":[0],"retrieval":[1,16,58,79,84,164,178],"requires":[2],"the":[3,7,19,31,38,57,73,78,83,100,134],"system":[4],"to":[5],"bridge":[6],"heterogenous":[8],"gap":[9],"between":[10],"vision":[11],"and":[12,103,122,145,158],"language":[13],"for":[14,22],"accurate":[15],"while":[17,81,118],"keeping":[18],"network":[20],"lightweight-enough":[21],"efficient":[23],"retrieval.":[24,126],"Existing":[25],"trade-off":[26],"solutions":[27],"mainly":[28],"study":[29],"from":[30],"view":[32],"of":[33,72,136,149,174],"incorporating":[34],"cross-modal":[35,113],"interactions":[36,115],"with":[37,172],"independent-embedding":[39,74,139],"framework":[40],"or":[41,52],"leveraging":[42],"stronger":[43],"pre-trained":[44],"encoders,":[45],"which":[46,76],"still":[47],"demand":[48],"time-consuming":[49],"similarity":[50],"measurement":[51],"heavyweight":[53],"model":[54],"structure":[55],"in":[56,147,177],"stage.":[59],"In":[60],"this":[61],"work,":[62],"we":[63],"propose":[64],"an":[65],"image-text":[66,96],"alignment":[67,97],"module":[68],"SelfAlign":[69,89,131],"on":[70,152],"top":[71],"framework,":[75],"improves":[77],"accuracy":[80,135,165],"maintains":[82],"efficiency":[85],"without":[86],"extra":[87],"supervision.":[88],"contains":[90],"two":[91],"collaborative":[92],"sub-modules":[93],"that":[94],"force":[95],"at":[98],"both":[99],"concept":[101],"level":[102,105],"context":[104],"by":[106,142],"self-supervised":[107],"contrastive":[108],"learning.":[109],"It":[110],"doesn't":[111],"require":[112],"embedding":[114],"during":[116,125],"training":[117],"maintaining":[119],"independent":[120],"image":[121],"text":[123],"encoders":[124],"With":[127],"comparable":[128],"time":[129],"cost,":[130],"consistently":[132],"boosts":[133],"state-of-the-art":[137],"non-pre-training":[138],"models":[140,171],"respectively":[141],"9.1%,":[143],"4.2%,":[144],"6.6%":[146],"terms":[148],"R@sum":[150],"score":[151],"Flickr30":[153],"K,":[154],"MS-COCO":[155,159],"1":[156],"K":[157,161],"5":[160],"datasets.":[162],"The":[163,180],"also":[166],"outperforms":[167],"most":[168],"existing":[169],"interactive-embedding":[170],"orders":[173],"magnitude":[175],"decrease":[176],"time.":[179],"source":[181],"code":[182],"is":[183],"available":[184],"at:":[185],"<uri":[186],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[187],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/Zjamie813/SelfAlign</uri>":[188],".":[189]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}