{"id":"https://openalex.org/W4415708388","doi":"https://doi.org/10.1109/icme59968.2025.11208912","title":"Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrieval","display_name":"Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrieval","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708388","doi":"https://doi.org/10.1109/icme59968.2025.11208912"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11208912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5045191293","display_name":"Junyang Chen","orcid":"https://orcid.org/0000-0002-1139-8654"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junyang Chen","raw_affiliation_strings":["Sun Yat-Sen University,School of Computer Science and Engineering,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University,School of Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076868018","display_name":"Hanjiang Lai","orcid":"https://orcid.org/0000-0001-8057-6744"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanjiang Lai","raw_affiliation_strings":["Sun Yat-Sen University,School of Computer Science and Engineering,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University,School of Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5045191293"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":1.428,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86945091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.73580002784729,"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":0.73580002784729,"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":0.08309999853372574,"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":0.053300000727176666,"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/focus","display_name":"Focus (optics)","score":0.6883000135421753},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6057999730110168},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6047000288963318},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5931000113487244},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4092000126838684},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4066999852657318},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.32359999418258667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7918999791145325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7167999744415283},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6883000135421753},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6057999730110168},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6047000288963318},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5931000113487244},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5325000286102295},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4066999852657318},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.32359999418258667},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11208912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W2185175083","https://openalex.org/W2905544595","https://openalex.org/W3172514680","https://openalex.org/W3175684172","https://openalex.org/W3203247393","https://openalex.org/W4292828970","https://openalex.org/W4312825288","https://openalex.org/W4313156423","https://openalex.org/W4313172370","https://openalex.org/W4386065506","https://openalex.org/W4386071700","https://openalex.org/W4386076084","https://openalex.org/W4390873539","https://openalex.org/W4393159265","https://openalex.org/W4394625619","https://openalex.org/W4402727158"],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"composed":[1],"image":[2,13,21,73,125,156],"retrieval":[3],"(ZS-CIR),":[4],"which":[5,90,149],"takes":[6],"a":[7,11,15,19,82,141,167],"textual":[8],"modification":[9],"and":[10,28,50,85,98,153,204],"reference":[12],"as":[14,116],"query":[16],"to":[17,67,104,127,157,176],"retrieve":[18],"target":[20],"without":[22],"triplet":[23,133],"labeling,":[24],"has":[25],"gained":[26],"more":[27,29],"attention.":[30],"Current":[31],"ZS-CIR":[32,198],"research":[33],"relies":[34],"mainly":[35],"on":[36,60,196],"the":[37,47,57,62,69,72,92,95,99,106,110,114,117,151,154,159,162,170,186,193],"generalization":[38],"ability":[39],"of":[40,71,113,161,189],"pre-trained":[41,48,86,96,145],"vision":[42],"language":[43],"models":[44,195],"(VLMs).":[45],"However,":[46],"VLMs":[49,58,97,115],"CIR":[51,65,101,118],"tasks":[52],"have":[53],"substantial":[54],"discrepancies,":[55],"where":[56,120],"focus":[59],"learning":[61,112],"similarities":[63],"but":[64,143],"aims":[66],"learn":[68,158,175],"modifications":[70,160],"guided":[74],"by":[75],"text.":[76],"In":[77],"this":[78],"paper,":[79],"we":[80,108,121,139],"introduce":[81],"novel":[83,144],"unlabeled":[84],"masked":[87,146,155,172],"tuning":[88,147,173],"approach,":[89],"reduces":[91],"gap":[93],"between":[94],"downstream":[100],"task.":[102],"First,":[103],"reduce":[105],"gap,":[107],"reformulate":[109],"contrastive":[111],"task,":[119],"randomly":[122],"mask":[123],"input":[124],"patches":[126],"generate":[128],"\u27e8masked":[129],"image,":[130],"text,":[131],"image\u27e9":[132],"from":[134],"an":[135],"image-text":[136],"pair.":[137],"Then,":[138],"propose":[140],"simple":[142,168],"method,":[148],"uses":[150],"text":[152],"original":[163],"image.":[164],"With":[165],"such":[166],"design,":[169],"proposed":[171],"can":[174],"better":[177],"capture":[178],"fine-grained":[179],"text-guided":[180],"modifications.":[181],"Extensive":[182],"experimental":[183],"results":[184],"demonstrate":[185],"significant":[187],"superiority":[188],"our":[190],"approach":[191],"over":[192],"baseline":[194],"four":[197],"datasets,":[199],"including":[200],"FashionIQ,":[201],"CIRR,":[202],"CIRCO,":[203],"GeneCIS.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}