{"id":"https://openalex.org/W4225166070","doi":"https://doi.org/10.24963/ijcai.2022/759","title":"Image-text Retrieval: A Survey on Recent Research and Development","display_name":"Image-text Retrieval: A Survey on Recent Research and Development","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4225166070","doi":"https://doi.org/10.24963/ijcai.2022/759"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/759","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/759","pdf_url":"https://www.ijcai.org/proceedings/2022/0759.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0759.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035837633","display_name":"Min Cao","orcid":"https://orcid.org/0000-0002-4497-5841"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Cao","raw_affiliation_strings":["Soochow University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009555060","display_name":"Shiping Li","orcid":"https://orcid.org/0000-0001-7639-2985"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiping Li","raw_affiliation_strings":["Soochow University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100657513","display_name":"Juntao Li","orcid":"https://orcid.org/0000-0002-3288-4395"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juntao Li","raw_affiliation_strings":["Soochow University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["Shandong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100402911","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-3895-5510"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen","Soochow University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Soochow University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":89,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5410","last_page":"5417"},"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":0.9995999932289124,"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":0.9952999949455261,"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/computer-science","display_name":"Computer science","score":0.6620967984199524},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6057589650154114},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5848568677902222},{"id":"https://openalex.org/keywords/pace","display_name":"Pace","score":0.5796388387680054},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5755640268325806},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.563540518283844},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5512361526489258},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5389929413795471},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4960375726222992},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4110490083694458},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.39254581928253174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28683343529701233},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2518048882484436},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09655120968818665},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0780358612537384}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6620967984199524},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6057589650154114},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5848568677902222},{"id":"https://openalex.org/C2777526511","wikidata":"https://www.wikidata.org/wiki/Q691543","display_name":"Pace","level":2,"score":0.5796388387680054},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5755640268325806},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.563540518283844},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5512361526489258},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5389929413795471},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4960375726222992},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4110490083694458},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39254581928253174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28683343529701233},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2518048882484436},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09655120968818665},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0780358612537384},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/759","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/759","pdf_url":"https://www.ijcai.org/proceedings/2022/0759.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/759","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/759","pdf_url":"https://www.ijcai.org/proceedings/2022/0759.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G795695972","display_name":null,"funder_award_id":"NSFC 62002252","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327518","display_name":"Priority Academic Program Development of Jiangsu Higher Education Institutions","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4225166070.pdf","grobid_xml":"https://content.openalex.org/works/W4225166070.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W2123024445","https://openalex.org/W2604880013","https://openalex.org/W2606473278","https://openalex.org/W2619383789","https://openalex.org/W2774267535","https://openalex.org/W2895249671","https://openalex.org/W2962964995","https://openalex.org/W2963187862","https://openalex.org/W2964187781","https://openalex.org/W2966715458","https://openalex.org/W2968124245","https://openalex.org/W2981586349","https://openalex.org/W2985951359","https://openalex.org/W2988823324","https://openalex.org/W2990571534","https://openalex.org/W2994818707","https://openalex.org/W2998356391","https://openalex.org/W3001555892","https://openalex.org/W3007731621","https://openalex.org/W3014611590","https://openalex.org/W3029678209","https://openalex.org/W3035454331","https://openalex.org/W3035485997","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3038476992","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3110042533","https://openalex.org/W3120581333","https://openalex.org/W3126337491","https://openalex.org/W3126792443","https://openalex.org/W3133825286","https://openalex.org/W3155230099","https://openalex.org/W3165938948","https://openalex.org/W3168433561","https://openalex.org/W3171668871","https://openalex.org/W3173220247","https://openalex.org/W3175740157","https://openalex.org/W3176013197","https://openalex.org/W3176451698","https://openalex.org/W3176824248","https://openalex.org/W3177224328","https://openalex.org/W3184735396","https://openalex.org/W3184784418","https://openalex.org/W3190055600","https://openalex.org/W3193171560","https://openalex.org/W3207798279","https://openalex.org/W3212456749","https://openalex.org/W3212610063","https://openalex.org/W4287394079","https://openalex.org/W4288102874","https://openalex.org/W4298038525","https://openalex.org/W4303414778","https://openalex.org/W4312784228"],"related_works":["https://openalex.org/W2386723501","https://openalex.org/W2387879414","https://openalex.org/W2390304029","https://openalex.org/W2354923724","https://openalex.org/W2146830340","https://openalex.org/W2377101853","https://openalex.org/W2362180844","https://openalex.org/W2105573916","https://openalex.org/W2378405797","https://openalex.org/W627697492"],"abstract_inverted_index":{"In":[0],"the":[1,14,31,34,41,56,77,81,92,96,102,109,118,124,130,141,145,158,161],"past":[2],"few":[3],"years,":[4],"cross-modal":[5,119],"image-text":[6],"retrieval":[7,42],"(ITR)":[8],"has":[9],"experienced":[10],"increased":[11],"interest":[12],"in":[13],"research":[15,21],"community":[16],"due":[17],"to":[18],"its":[19],"excellent":[20],"value":[22],"and":[23,40,52,72,134,139],"broad":[24],"real-world":[25],"application.":[26],"It":[27],"is":[28,99],"designed":[29],"for":[30,137],"scenarios":[32],"where":[33],"queries":[35],"are":[36,155],"from":[37,44,59,84],"one":[38],"modality":[39],"galleries":[43],"another":[45],"modality.":[46],"This":[47],"paper":[48],"presents":[49],"a":[50,114],"comprehensive":[51],"up-to-date":[53],"survey":[54],"on":[55,95],"ITR":[57,65,82,97,121,147],"approaches":[58,83,122],"four":[60],"perspectives.":[61,87],"By":[62],"dissecting":[63],"an":[64],"system":[66,98],"into":[67],"two":[68,86],"processes:":[69],"feature":[70,73],"extraction":[71],"alignment,":[74],"we":[75,111,128],"summarize":[76],"recent":[78],"advance":[79],"of":[80,90,117,160],"these":[85],"On":[88],"top":[89],"this,":[91],"efficiency-focused":[93],"study":[94],"introduced":[100],"as":[101,123],"third":[103],"perspective.":[104,126],"To":[105],"keep":[106],"pace":[107],"with":[108],"times,":[110],"also":[112],"provide":[113],"pioneering":[115],"overview":[116],"pre-training":[120],"fourth":[125],"Finally,":[127],"outline":[129],"common":[131],"benchmark":[132],"datasets":[133],"evaluation":[135],"metric":[136],"ITR,":[138],"conduct":[140],"accuracy":[142],"comparison":[143],"among":[144],"representative":[146],"approaches.":[148],"Some":[149],"critical":[150],"yet":[151],"less":[152],"studied":[153],"issues":[154],"discussed":[156],"at":[157],"end":[159],"paper.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":31},{"year":2023,"cited_by_count":18}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}