{"id":"https://openalex.org/W4413277869","doi":"https://doi.org/10.1109/tmm.2025.3599088","title":"Scale Up Composed Image Retrieval Learning via Modification Text Generation","display_name":"Scale Up Composed Image Retrieval Learning via Modification Text Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413277869","doi":"https://doi.org/10.1109/tmm.2025.3599088"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3599088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3599088","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5028344824","display_name":"Yinan Zhou","orcid":"https://orcid.org/0009-0003-2211-6688"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yinan Zhou","raw_affiliation_strings":["School of Electronics and Information Engineering, Xi’an Jiaotong University, Xi’an, China","School of Electronics and Information Engineering, Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Engineering, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Electronics and Information Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101651167","display_name":"Yaxiong Wang","orcid":"https://orcid.org/0000-0001-6596-8117"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaxiong Wang","raw_affiliation_strings":["School of Electronics and Information Engineering, Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haokun Lin","orcid":"https://orcid.org/0009-0000-1084-7115"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haokun Lin","raw_affiliation_strings":["School of Artificial Intelligence, University of the Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100410908","display_name":"Chen Ma","orcid":"https://orcid.org/0000-0001-7933-9813"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chen Ma","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China","Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100635252","display_name":"Li Zhu","orcid":"https://orcid.org/0000-0003-2136-3196"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhu","raw_affiliation_strings":["School of Electronics and Information Engineering, Xi’an Jiaotong University, Xi’an, China","School of Electronics and Information Engineering, Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Engineering, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Electronics and Information Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034162160","display_name":"Zhedong Zheng","orcid":"https://orcid.org/0000-0002-2434-9050"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Zhedong Zheng","raw_affiliation_strings":["Faculty of Science and Technology, University of Macau, Macau, China","Faculty of Science and Technology, and Institute of Collaborative Innovation, University of Macau, Macau, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Science and Technology, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498"]},{"raw_affiliation_string":"Faculty of Science and Technology, and Institute of Collaborative Innovation, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5028344824"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":1.2181,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82489514,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"27","issue":null,"first_page":"7510","last_page":"7521"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9927999973297119,"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":0.9927999973297119,"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":0.9180999994277954,"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/computer-science","display_name":"Computer science","score":0.8167669177055359},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5659341812133789},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4978950023651123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48406925797462463},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.38382917642593384},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3798159062862396},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3658004403114319},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3462502360343933}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8167669177055359},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5659341812133789},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4978950023651123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48406925797462463},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.38382917642593384},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3798159062862396},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3658004403114319},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3462502360343933},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3599088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3599088","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321019","display_name":"University Grants Committee","ror":"https://ror.org/00djwmt25"},{"id":"https://openalex.org/F4320322841","display_name":"Universidade de Macau","ror":"https://ror.org/01r4q9n85"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2392997304","https://openalex.org/W2471768434","https://openalex.org/W2741217081","https://openalex.org/W2905544595","https://openalex.org/W2963530300","https://openalex.org/W2964211610","https://openalex.org/W3016211260","https://openalex.org/W3092962760","https://openalex.org/W3172514680","https://openalex.org/W3175684172","https://openalex.org/W3203247393","https://openalex.org/W3204588463","https://openalex.org/W4296915201","https://openalex.org/W4304091775","https://openalex.org/W4312933868","https://openalex.org/W4313855701","https://openalex.org/W4375801927","https://openalex.org/W4376481269","https://openalex.org/W4383337770","https://openalex.org/W4386065506","https://openalex.org/W4386071700","https://openalex.org/W4386075952","https://openalex.org/W4386076215","https://openalex.org/W4386076522","https://openalex.org/W4386273457","https://openalex.org/W4386290297","https://openalex.org/W4387968123","https://openalex.org/W4387969466","https://openalex.org/W4390873539","https://openalex.org/W4394564353","https://openalex.org/W4394625619","https://openalex.org/W4399883643","https://openalex.org/W4400530983","https://openalex.org/W4402713111","https://openalex.org/W4402727158","https://openalex.org/W4403792064","https://openalex.org/W4403947192"],"related_works":["https://openalex.org/W2087793626","https://openalex.org/W2755342338","https://openalex.org/W2779427294","https://openalex.org/W2052697133","https://openalex.org/W2775347418","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W3116076068","https://openalex.org/W3003936178","https://openalex.org/W2145652935"],"abstract_inverted_index":{"Composed":[0],"Image":[1],"Retrieval":[2],"(CIR)":[3],"aims":[4],"to":[5,32,48,53,95,116,122,133,177],"search":[6],"an":[7,150],"image":[8,17,120],"of":[9,14,106,190],"interest":[10],"using":[11],"a":[12,15,67,129,163],"combination":[13],"reference":[16,124],"and":[18,36,75,85,143,158,194,207,211],"modification":[19,68,114,175],"text":[20,69,115,176],"as":[21],"the":[22,50,55,59,78,83,92,118,123,136,140,144,155,169,174,182,188,191,205],"query.":[23],"Despite":[24],"recent":[25],"advancements,":[26],"this":[27,43,45],"task":[28],"remains":[29],"challenging":[30],"due":[31],"limited":[33],"training":[34,51,56,66],"data":[35],"laborious":[37],"triplet":[38,157],"annotation":[39],"processes.":[40],"To":[41],"address":[42],"issue,":[44],"paper":[46],"proposes":[47],"synthesize":[49,112],"triplets":[52,193],"augment":[54],"resource":[57],"for":[58],"CIR":[60,79],"problem.":[61],"Specifically,":[62],"we":[63,90,110,127],"commence":[64],"by":[65,167],"generator":[70,94],"exploiting":[71],"large-scale":[72],"multimodal":[73,141],"models":[74],"scale":[76],"up":[77],"learning":[80],"throughout":[81],"both":[82,154,204],"pretraining":[84],"fine-tuning":[86],"stages.":[87],"During":[88],"pretraining,":[89],"leverage":[91],"trained":[93],"directly":[96],"create":[97],"Modification":[98],"Text-oriented":[99],"Synthetic":[100],"Triplets":[101],"(MTST)":[102],"conditioned":[103],"on":[104,203],"pairs":[105],"images.":[107],"For":[108],"fine-tuning,":[109],"first":[111],"reverse":[113],"connect":[117],"target":[119,145,183],"back":[121],"image.":[125,146,184],"Subsequently,":[126],"devise":[128],"two-hop":[130],"alignment":[131,180],"strategy":[132],"incrementally":[134],"close":[135],"semantic":[137],"gap":[138],"between":[139],"pair":[142],"We":[147],"initially":[148],"learn":[149],"implicit":[151,170],"prototype":[152,171],"utilizing":[153],"original":[156],"its":[159],"reversed":[160],"version":[161],"in":[162],"cycle":[164],"manner,":[165],"followed":[166],"combining":[168],"feature":[172],"with":[173,181],"facilitate":[178],"accurate":[179],"Extensive":[185],"experiments":[186],"validate":[187],"efficacy":[189],"generated":[192],"confirm":[195],"that":[196],"our":[197],"proposed":[198],"methodology":[199],"attains":[200],"competitive":[201],"recall":[202],"CIRR":[206],"FashionIQ":[208],"benchmarks.":[209],"Codes":[210],"datasets":[212],"will":[213],"be":[214],"made":[215],"publicly":[216],"accessible.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}