{"id":"https://openalex.org/W4366851068","doi":"https://doi.org/10.1145/3539618.3591758","title":"Rethinking Benchmarks for Cross-modal Image-text Retrieval","display_name":"Rethinking Benchmarks for Cross-modal Image-text Retrieval","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4366851068","doi":"https://doi.org/10.1145/3539618.3591758"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3591758","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2304.10824","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012716072","display_name":"Weijing Chen","orcid":"https://orcid.org/0000-0001-9371-5256"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weijing Chen","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100599428","display_name":"Linli Yao","orcid":"https://orcid.org/0000-0002-9809-8864"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linli Yao","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009985839","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0001-6486-6020"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5012716072"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":2.3879,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90566924,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1241","last_page":"1251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9983000159263611,"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":0.9970999956130981,"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":0.8609466552734375},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6225460171699524},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6171938180923462},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5922912359237671},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5695216059684753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5405195951461792},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5394338965415955},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5287489295005798},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.5196453332901001},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5134114027023315},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.502758264541626},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5017294883728027},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4664435088634491},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46071797609329224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8609466552734375},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6225460171699524},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6171938180923462},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5922912359237671},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5695216059684753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5405195951461792},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5394338965415955},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5287489295005798},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5196453332901001},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5134114027023315},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.502758264541626},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5017294883728027},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4664435088634491},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46071797609329224},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3539618.3591758","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2304.10824","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.10824","pdf_url":"https://arxiv.org/pdf/2304.10824","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:2304.10824","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.10824","pdf_url":"https://arxiv.org/pdf/2304.10824","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":0.5799999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4668466387","display_name":null,"funder_award_id":"6207246","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8012818879","display_name":null,"funder_award_id":"No. 62072462","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8390650537","display_name":null,"funder_award_id":"62072462","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4366851068.pdf","grobid_xml":"https://content.openalex.org/works/W4366851068.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2077069816","https://openalex.org/W2185175083","https://openalex.org/W2187089797","https://openalex.org/W2250384498","https://openalex.org/W2560835477","https://openalex.org/W2886641317","https://openalex.org/W2911445777","https://openalex.org/W2912500072","https://openalex.org/W2913602408","https://openalex.org/W2913668833","https://openalex.org/W2913954081","https://openalex.org/W2914304175","https://openalex.org/W2964727037","https://openalex.org/W2965848243","https://openalex.org/W2981586349","https://openalex.org/W2982078236","https://openalex.org/W2998356391","https://openalex.org/W3090449556","https://openalex.org/W3092820619","https://openalex.org/W3118694826","https://openalex.org/W3153469116","https://openalex.org/W3155230099","https://openalex.org/W3173909648","https://openalex.org/W3177224328","https://openalex.org/W3184784418","https://openalex.org/W6600553734"],"related_works":["https://openalex.org/W2393699422","https://openalex.org/W2168037874","https://openalex.org/W2387268739","https://openalex.org/W2135728080","https://openalex.org/W2379546782","https://openalex.org/W2534443799","https://openalex.org/W2148968119","https://openalex.org/W2391460410","https://openalex.org/W3196281958","https://openalex.org/W1595649729"],"abstract_inverted_index":{"Image-text":[0],"retrieval,":[1,10],"as":[2],"a":[3,96,154],"fundamental":[4],"and":[5,26,63,74,101,117,123,130,230],"important":[6],"branch":[7],"of":[8,19,41,85,99,185,193,223],"information":[9],"has":[11],"attracted":[12],"extensive":[13,200],"research":[14,244],"attentions.":[15],"The":[16,92,202],"main":[17],"challenge":[18],"this":[20,66],"task":[21],"is":[22,94],"cross-modal":[23,35,89,246],"semantic":[24,36,90,197,217],"understanding":[25],"matching.":[27,37,91],"Some":[28],"recent":[29],"works":[30],"focus":[31],"more":[32,145],"on":[33,56,87,109,133,177,195,245],"fine-grained":[34,88,196,216],"With":[38],"the":[39,70,82,104,110,114,120,125,134,139,149,183,191,207],"prevalence":[40],"large":[42,97],"scale":[43],"multimodal":[44],"pretraining":[45],"models,":[46],"several":[47],"state-of-the-art":[48,208],"models":[49,86,176,194,209],"(e.g.":[50],"X-VLM)":[51],"have":[52,210],"achieved":[53],"near-perfect":[54],"performance":[55],"widely-used":[57],"image-text":[58,174],"retrieval":[59,175],"benchmarks,":[60],"i.e.":[61],"MSCOCO-Test-5K":[62],"Flickr30K-Test-1K.":[64],"In":[65],"paper,":[67],"we":[68,112,137,152,171,238],"review":[69],"two":[71],"common":[72],"benchmarks":[73,105,122,127,180],"observe":[75],"that":[76,95,205],"they":[77],"are":[78,106,234],"insufficient":[79],"to":[80,159,181],"assess":[81],"true":[83],"capability":[84,192],"reason":[93],"amount":[98],"images":[100,116],"texts":[102,118],"in":[103,119,215,220,226],"coarse-grained.":[107],"Based":[108],"observation,":[111],"renovate":[113],"coarse-grained":[115,161],"old":[121],"establish":[124],"improved":[126,231],"called":[128],"MSCOCO-FG":[129],"Flickr30K-FG.":[131],"Specifically,":[132],"image":[135,141],"side,":[136,151],"enlarge":[138],"original":[140],"pool":[142],"by":[143],"adopting":[144],"similar":[146],"images.":[147,227],"On":[148],"text":[150],"propose":[153],"novel":[155],"semi-automatic":[156],"renovation":[157],"approach":[158],"refine":[160],"sentences":[162],"into":[163],"finer-grained":[164],"ones":[165],"with":[166],"little":[167],"human":[168],"effort.":[169],"Furthermore,":[170],"evaluate":[172],"representative":[173],"our":[178,186],"new":[179],"demonstrate":[182],"effectiveness":[184],"method.":[187],"We":[188],"also":[189],"analyze":[190],"comprehension":[198],"through":[199],"experiments.":[201],"results":[203],"show":[204],"even":[206],"much":[211],"room":[212],"for":[213],"improvement":[214],"understanding,":[218],"especially":[219],"distinguishing":[221],"attributes":[222],"close":[224],"objects":[225],"Our":[228],"code":[229],"benchmark":[232],"datasets":[233],"publicly":[235],"available1":[236],"which":[237],"hope":[239],"will":[240],"inspire":[241],"further":[242],"in-depth":[243],"retrieval.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":10}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}