{"id":"https://openalex.org/W7164832421","doi":"https://doi.org/10.1145/3805622.3810604","title":"RankVR: Low-Rank Structure Perception and Value Recalibration for Robust Composed Image Retrieval","display_name":"RankVR: Low-Rank Structure Perception and Value Recalibration for Robust Composed Image Retrieval","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164832421","doi":"https://doi.org/10.1145/3805622.3810604"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810604","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810604","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810604","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129731238","display_name":"Jiale Huang","orcid":null},"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":"Jiale Huang","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0002-9435-4127","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136792084","display_name":"Zixu Li","orcid":"https://orcid.org/0009-0001-5136-159X"},"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":"Zixu Li","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0001-5136-159X","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050782735","display_name":"Zhiheng Fu","orcid":"https://orcid.org/0009-0007-7724-5662"},"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":"Zhiheng Fu","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0007-7724-5662","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125059455","display_name":"Z Chen","orcid":null},"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":"Zhiwei Chen","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0003-0365-8553","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126005311","display_name":"Qinlei Huang","orcid":null},"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":"Qinlei Huang","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0009-0318-7599","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101875643","display_name":"Yupeng Hu","orcid":"https://orcid.org/0000-0002-5653-8286"},"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":"Yupeng Hu","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-5653-8286","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93680368,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"269","last_page":"278"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.7491999864578247,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.7491999864578247,"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":0.18019999563694,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.007499999832361937,"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/value","display_name":"Value (mathematics)","score":0.44190001487731934},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.41510000824928284},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4016999900341034},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.34850001335144043},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3452000021934509},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3149000108242035}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6380000114440918},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5493000149726868},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5257999897003174},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.44190001487731934},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.41510000824928284},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3052000105381012},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.29429998993873596},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.29010000824928284},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810604","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810604","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810604","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810604","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3981135610","display_name":null,"funder_award_id":"62276155","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7882649824","display_name":null,"funder_award_id":"62576195","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2115091888","https://openalex.org/W2905544595","https://openalex.org/W2972137450","https://openalex.org/W3026458074","https://openalex.org/W3034623328","https://openalex.org/W3157181916","https://openalex.org/W3172514680","https://openalex.org/W3174026887","https://openalex.org/W3203247393","https://openalex.org/W3206142385","https://openalex.org/W4224929299","https://openalex.org/W4256004654","https://openalex.org/W4312472480","https://openalex.org/W4321488152","https://openalex.org/W4375801803","https://openalex.org/W4382461147","https://openalex.org/W4385805009","https://openalex.org/W4386527955","https://openalex.org/W4387968356","https://openalex.org/W4390872636","https://openalex.org/W4391941146","https://openalex.org/W4393149123","https://openalex.org/W4393170802","https://openalex.org/W4396594821","https://openalex.org/W4402715906","https://openalex.org/W4402753981","https://openalex.org/W4403791316","https://openalex.org/W4403791324","https://openalex.org/W4408345919","https://openalex.org/W4408354931","https://openalex.org/W4409347665","https://openalex.org/W4409367947","https://openalex.org/W4412945336","https://openalex.org/W4413147218","https://openalex.org/W4415536769","https://openalex.org/W4415538366","https://openalex.org/W4415795828","https://openalex.org/W4415797492","https://openalex.org/W4415798008","https://openalex.org/W4416183038","https://openalex.org/W4417073166","https://openalex.org/W4417400953","https://openalex.org/W7137960719","https://openalex.org/W7138107458","https://openalex.org/W7138232037","https://openalex.org/W7138238529","https://openalex.org/W7140086938","https://openalex.org/W7140557520","https://openalex.org/W7155092706","https://openalex.org/W7160118679"],"related_works":[],"abstract_inverted_index":{"Composed":[0],"Image":[1],"Retrieval":[2],"(CIR)":[3],"constitutes":[4],"a":[5,90,95],"pivotal":[6],"paradigm":[7],"requiring":[8],"models":[9],"to":[10,93,126,154],"perform":[11],"joint":[12],"reasoning":[13],"on":[14,44,190],"reference":[15],"images":[16],"and":[17,56,79,103,164,193],"modification":[18],"texts.":[19],"However,":[20],"the":[21,110,119,123,147,169,191],"prevalence":[22],"of":[23,76,122,172,178],"Noisy":[24],"Triplet":[25],"Correspondence":[26],"(NTC)":[27],"in":[28,209],"large-scale":[29],"datasets":[30,196],"severely":[31],"constrains":[32],"model":[33,98],"performance.":[34],"Existing":[35],"denoising":[36],"methods":[37],"either":[38],"target":[39],"binary":[40],"mismatches":[41],"or":[42],"rely":[43],"scalar-based":[45],"point-wise":[46],"estimation,":[47],"neglecting":[48],"rich":[49],"global":[50,100],"structural":[51,131],"correlations":[52],"among":[53],"sample":[54],"populations":[55],"dynamic":[57,104],"value":[58,105,171],"variations":[59],"during":[60],"training,":[61],"thereby":[62],"yielding":[63],"suboptimal":[64],"results.":[65],"This":[66],"paper":[67],"identifies":[68,138],"two":[69],"critical":[70],"unresolved":[71],"challenges:":[72],"Global":[73,111],"Structural":[74],"Inconsistency":[75],"Semantic":[77,149],"Correlations":[78],"Hard":[80],"Sample":[81],"Discrimination":[82],"Uncertainty.":[83],"To":[84],"address":[85],"these,":[86],"we":[87,108,145],"propose":[88],"RankVR,":[89],"framework":[91],"designed":[92],"construct":[94],"robust":[96],"CIR":[97],"via":[99],"structure":[101],"consistency":[102],"perception.":[106],"Specifically,":[107],"introduce":[109],"Structure":[112],"Consistency":[113],"Perception":[114],"(GSCP)":[115],"module,":[116],"which":[117],"utilizes":[118],"Effective":[120],"Rank":[121],"Correlation":[124],"Matrix":[125],"decouple":[127],"clean":[128,158],"samples":[129,139,180],"from":[130],"noise.":[132],"By":[133,160],"measuring":[134],"rank":[135],"difference,":[136],"GSCP":[137],"disrupting":[140],"macroscopic":[141],"semantic":[142,170],"symmetry.":[143],"Furthermore,":[144],"develop":[146],"Adaptive":[148],"Value":[150],"Calibration":[151],"(ASVC)":[152],"module":[153],"distinguish":[155],"high-value":[156],"hard":[157,179],"samples.":[159],"integrating":[161],"training":[162],"potential":[163],"reliability,":[165],"it":[166],"dynamically":[167],"quantifies":[168],"each":[173],"triplet,":[174],"ensuring":[175],"effective":[176],"utilization":[177],"while":[181],"suppressing":[182],"noise":[183],"characterized":[184],"by":[185],"logical":[186],"conflicts.":[187],"Extensive":[188],"experiments":[189],"FashionIQ":[192],"CIRR":[194],"benchmark":[195],"demonstrate":[197],"that":[198],"RankVR":[199],"significantly":[200],"outperforms":[201],"existing":[202],"state-of-the-art":[203],"methods,":[204],"validating":[205],"its":[206],"superior":[207],"robustness":[208],"noisy":[210],"environments.":[211]},"counts_by_year":[],"updated_date":"2026-06-17T06:14:20.161405","created_date":"2026-06-16T00:00:00"}