{"id":"https://openalex.org/W7154830098","doi":"https://doi.org/10.1016/j.patcog.2026.113724","title":"BenchCIR: Benchmarking robustness in composed image retrieval across modalities","display_name":"BenchCIR: Benchmarking robustness in composed image retrieval across modalities","publication_year":2026,"publication_date":"2026-04-18","ids":{"openalex":"https://openalex.org/W7154830098","doi":"https://doi.org/10.1016/j.patcog.2026.113724"},"language":"en","primary_location":{"id":"doi:10.1016/j.patcog.2026.113724","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.113724","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.patcog.2026.113724","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077534756","display_name":"Shitong Sun","orcid":"https://orcid.org/0000-0003-1825-655X"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shitong Sun","raw_affiliation_strings":["Queen Mary University of London, London, E1 4NS, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London, London, E1 4NS, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041574741","display_name":"Qilei Li","orcid":"https://orcid.org/0000-0002-9675-9016"},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qilei Li","raw_affiliation_strings":["Laboratory for Artificial Intelligence and New Forms of Education, Central China Normal University, Wuhan, 430079, Hubei, China","National Engineering Research Center of Educational Big Data, Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan, 430079, Hubei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory for Artificial Intelligence and New Forms of Education, Central China Normal University, Wuhan, 430079, Hubei, China","institution_ids":["https://openalex.org/I40963666"]},{"raw_affiliation_string":"National Engineering Research Center of Educational Big Data, Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan, 430079, Hubei, China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133941416","display_name":"Shaogang Gong","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shaogang Gong","raw_affiliation_strings":["Queen Mary University of London, London, E1 4NS, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London, London, E1 4NS, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133928617","display_name":"Weitong Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Weitong Cai","raw_affiliation_strings":["Queen Mary University of London, London, E1 4NS, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London, London, E1 4NS, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133952568","display_name":"Philip Torr","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip Torr","raw_affiliation_strings":["University of Oxford, Oxford, OX1 2JD, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, OX1 2JD, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133946741","display_name":"Jindong Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jindong Gu","raw_affiliation_strings":["University of Oxford, Oxford, OX1 2JD, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, OX1 2JD, UK","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5041574741"],"corresponding_institution_ids":["https://openalex.org/I40963666"],"apc_list":{"value":2710,"currency":"USD","value_usd":2710},"apc_paid":{"value":2710,"currency":"USD","value_usd":2710},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.54925779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"179","issue":null,"first_page":"113724","last_page":"113724"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8464000225067139,"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":0.8464000225067139,"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":0.05570000037550926,"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":0.03920000046491623,"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/robustness","display_name":"Robustness (evolution)","score":0.849399983882904},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5892000198364258},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5509999990463257},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4311000108718872},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.42559999227523804},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.37290000915527344},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.33649998903274536},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.31310001015663147}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.849399983882904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7971000075340271},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5892000198364258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5705000162124634},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5509999990463257},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4471000134944916},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4311000108718872},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.42559999227523804},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.33649998903274536},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31529998779296875},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3070000112056732},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.27320000529289246},{"id":"https://openalex.org/C2780052074","wikidata":"https://www.wikidata.org/wiki/Q1128648","display_name":"Content-based image retrieval","level":4,"score":0.26919999718666077},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26159998774528503},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.patcog.2026.113724","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.113724","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.patcog.2026.113724","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.113724","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.786527156829834,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3807106378","display_name":null,"funder_award_id":"2025M781597","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320323173","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2561715562","https://openalex.org/W2905544595","https://openalex.org/W2964211610","https://openalex.org/W3026458074","https://openalex.org/W3175684172","https://openalex.org/W3203247393","https://openalex.org/W4292794825","https://openalex.org/W4296821576","https://openalex.org/W4312261477","https://openalex.org/W4312825288","https://openalex.org/W4313855701","https://openalex.org/W4324333799","https://openalex.org/W4394625619","https://openalex.org/W4395056490","https://openalex.org/W4396910060","https://openalex.org/W4399881520","https://openalex.org/W4405662451","https://openalex.org/W4408254499","https://openalex.org/W4411149047","https://openalex.org/W4413146661","https://openalex.org/W4413147218"],"related_works":[],"abstract_inverted_index":{"Composed":[0],"image":[1,16,35,58,89,120,193],"retrieval":[2,36,59,194],"aims":[3],"to":[4,22,33,37,61,101],"retrieve":[5],"images":[6,44],"based":[7],"on":[8],"a":[9,14,96,159,188],"query":[10],"that":[11,23],"consists":[12],"of":[13,56,69,87,99,118,140,154,216],"reference":[15,43],"and":[17,108,111,130,136,146,183,218],"text":[18,114,155,174],"describing":[19],"desired":[20],"modifications":[21],"image.":[24],"It":[25],"has":[26],"recently":[27],"attracted":[28],"attention":[29],"for":[30,95,132,190],"its":[31,51],"ability":[32],"tailor":[34],"user":[38],"intentions":[39],"by":[40,164],"combining":[41],"information-rich":[42],"with":[45,169,197],"concise":[46],"natural":[47,119],"language":[48],"instructions.":[49],"Despite":[50],"current":[52],"success,":[53],"the":[54,70,83,106,133,166,207,214],"robustness":[55,85,100,112,196],"composed":[57,88,192],"methods":[60],"either":[62],"(1)":[63],"common":[64,102],"corruptions":[65,145],"or":[66],"(2)":[67],"variations":[68,177],"textual":[71,107,148,219],"descriptions":[72],"have":[73],"never":[74],"been":[75],"systematically":[76],"evaluated.":[77],"In":[78],"this":[79],"paper,":[80],"we":[81,122,157,209],"perform":[82],"first":[84],"study":[86],"retrieval,":[90],"establishing":[91],"three":[92],"new":[93,125,160],"benchmarks":[94],"systematic":[97],"evaluation":[98,153,199],"corruption":[103],"(in":[104],"both":[105],"visual":[109,144,217],"domains)":[110],"in":[113,206,227],"understanding.":[115],"For":[116],"analysis":[117],"corruption,":[121],"introduce":[123,158,186],"two":[124],"large-scale":[126],"benchmark":[127],"datasets,":[128],"CIRR-C":[129],"FashionIQ-C,":[131],"open":[134],"domains":[135,138],"fashion":[137],"respectively\u2013both":[139],"which":[141],"feature":[142],"75":[143],"35":[147],"corruptions.":[149],"To":[150],"facilitate":[151],"robust":[152],"understanding,":[156],"diagnostic":[161],"dataset":[162,168],"CIRR-D":[163],"expanding":[165],"CIRR":[167],"synthetic":[170],"data,":[171],"specifically":[172],"probing":[173],"understanding":[175],"across":[176],"in:":[178],"numerical,":[179],"attribute,":[180],"object":[181],"removal,":[182],"background.":[184],"We":[185],"BenchCIR,":[187],"testbed":[189],"evaluating":[191],"model":[195,222],"standardized":[198],"protocols.":[200],"Through":[201],"benchmarking":[202],"ten":[203],"published":[204],"models":[205],"testbed,":[208],"reveal":[210],"insights":[211],"into":[212],"how":[213],"composition":[215],"modalities":[220],"affects":[221],"robustness.":[223],"The":[224],"code":[225],"is":[226],"https://suntongtongtong.github.io/BenchCIR/":[228]},"counts_by_year":[],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2026-04-19T00:00:00"}