{"id":"https://openalex.org/W4403780556","doi":"https://doi.org/10.1145/3664647.3681671","title":"ReCoS: A Novel Benchmark for Cross-Modal Image-Text Retrieval in Complex Real-Life Scenarios","display_name":"ReCoS: A Novel Benchmark for Cross-Modal Image-Text Retrieval in Complex Real-Life Scenarios","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780556","doi":"https://doi.org/10.1145/3664647.3681671"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681671","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-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/A5100369438","display_name":"Xiaojun Chen","orcid":"https://orcid.org/0000-0002-2818-4652"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaojun Chen","raw_affiliation_strings":["Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112045626","display_name":"Jin Lou","orcid":"https://orcid.org/0009-0009-3091-8270"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jimeng Lou","raw_affiliation_strings":["Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103240369","display_name":"Weiqiang Huang","orcid":"https://orcid.org/0000-0003-3877-5920"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxi Huang","raw_affiliation_strings":["Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102698196","display_name":"Ting Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131919","display_name":"Xi'an University of Technology","ror":"https://ror.org/038avdt50","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210131919"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Wan","raw_affiliation_strings":["Xi'an University of Technology, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xi'an University of Technology, Xi'an, China","institution_ids":["https://openalex.org/I4210131919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053100078","display_name":"Qin Zhang","orcid":"https://orcid.org/0000-0002-1449-5046"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Zhang","raw_affiliation_strings":["Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083369457","display_name":"Min Yang","orcid":"https://orcid.org/0000-0001-7345-5071"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Yang","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Sciences (CAS), Shenzhen, China, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Sciences (CAS), Shenzhen, China, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100369438"],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19167435,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9165","last_page":"9174"},"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":0.9993000030517578,"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":0.9968000054359436,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8266642093658447},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7837039232254028},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7314671277999878},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47000035643577576},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45469632744789124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4423012435436249},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4175340235233307},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36030352115631104},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07371148467063904},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.052997082471847534}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8266642093658447},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7837039232254028},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7314671277999878},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47000035643577576},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45469632744789124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4423012435436249},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4175340235233307},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36030352115631104},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07371148467063904},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.052997082471847534},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681671","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2185175083","https://openalex.org/W2606473278","https://openalex.org/W2883311563","https://openalex.org/W2962964995","https://openalex.org/W2963389687","https://openalex.org/W2964727037","https://openalex.org/W2965463054","https://openalex.org/W2982078236","https://openalex.org/W2988823324","https://openalex.org/W2997847174","https://openalex.org/W3035449864","https://openalex.org/W3035605030","https://openalex.org/W3035688398","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3118694826","https://openalex.org/W3173220247","https://openalex.org/W3208314443","https://openalex.org/W3213100861","https://openalex.org/W4312784228","https://openalex.org/W4366851068","https://openalex.org/W4386071498","https://openalex.org/W4389665280","https://openalex.org/W4390872633"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Image-text":[0],"retrieval":[1,93,104,178,187,205,222],"stands":[2],"as":[3,34],"a":[4,48,63,68,85,107,115,156],"pivotal":[5],"task":[6],"within":[7,207],"information":[8],"retrieval,":[9,55],"gaining":[10],"increasing":[11],"importance":[12],"with":[13,106],"the":[14,124,127,131,148,159,162,184,196,211,218],"rapid":[15],"advancements":[16],"in":[17,73,94,203,216,223,238],"Visual-Language":[18],"Pretraining":[19],"models.":[20],"However,":[21],"current":[22],"benchmarks":[23],"for":[24,47,53,90,213,233],"evaluating":[25],"these":[26],"models":[27],"face":[28],"limitations,":[29],"exemplified":[30],"by":[31,199],"instances":[32],"such":[33],"BLIP2":[35],"achieving":[36],"near-perfect":[37],"performance":[38],"on":[39,110,141,195],"existing":[40,99,142,200],"benchmarks.":[41],"In":[42],"response,":[43],"this":[44,80,239],"paper":[45],"advocates":[46],"more":[49,116],"robust":[50],"evaluation":[51,191],"benchmark":[52,65,87,166,229],"image-text":[54,92,221],"one":[56],"that":[57,172],"embraces":[58],"several":[59],"essential":[60],"characteristics.":[61],"Firstly,":[62],"comprehensive":[64],"should":[66],"cover":[67],"diverse":[69],"range":[70],"of":[71,119,126,133,139,150,161,220],"tasks":[72,206],"both":[74],"perception":[75],"and":[76,165,228,236],"cognition-based":[77,112,204],"retrieval.":[78],"Recognizing":[79],"need,":[81],"we":[82,129],"introduce":[83],"ReCoS,":[84],"novel":[86],"specifically":[88],"designed":[89],"cross-modal":[91],"complex":[95],"real-life":[96],"scenarios.":[97,225],"Unlike":[98],"benchmarks,":[100],"ReCoS":[101,168],"encompasses":[102],"12":[103],"tasks,":[105,113],"particular":[108],"focus":[109],"three":[111],"providing":[114],"holistic":[117],"assessment":[118],"model":[120],"capabilities.":[121],"To":[122],"ensure":[123],"novelty":[125],"benchmark,":[128],"emphasize":[130],"use":[132],"original":[134],"data":[135,151],"sources,":[136],"steering":[137],"clear":[138],"reliance":[140],"publicly":[143],"available":[144,232],"datasets":[145,230],"to":[146,154,183],"minimize":[147],"risk":[149],"leakage.":[152],"Additionally,":[153],"strike":[155],"balance":[157],"between":[158],"complexity":[160],"real":[163],"world":[164],"usability,":[167],"includes":[169],"text":[170],"descriptions":[171],"are":[173,231],"neither":[174],"overly":[175,179],"detailed,":[176],"making":[177],"simplistic,":[180],"nor":[181],"under-detailed":[182],"point":[185],"where":[186],"becomes":[188],"impossible.":[189],"Our":[190,226],"results":[192],"shed":[193],"light":[194],"challenges":[197],"faced":[198],"methods,":[201],"especially":[202],"ReCoS.":[208],"This":[209],"underscores":[210],"necessity":[212],"innovative":[214],"approaches":[215],"addressing":[217],"complexities":[219],"real-world":[224],"code":[227],"further":[234],"research":[235],"development":[237],"field":[240],"https://github.com/Bruce-XJChen/ReCos":[241]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}