{"id":"https://openalex.org/W4416251379","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228953","title":"Scaling Prompt Instructed Zero Shot Composed Image Retrieval with Image-Only Data","display_name":"Scaling Prompt Instructed Zero Shot Composed Image Retrieval with Image-Only Data","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251379","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228953"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228953","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5059407219","display_name":"Yiqun Duan","orcid":"https://orcid.org/0000-0003-1517-994X"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yiqun Duan","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102777273","display_name":"Sameera Ramasinghe","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sameera Ramasinghe","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071663279","display_name":"Stephen Jay Gould","orcid":"https://orcid.org/0000-0001-8929-7899"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stephen Gould","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039055995","display_name":"Thalaiyasingam Ajanthan","orcid":"https://orcid.org/0000-0002-6431-0775"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ajanthan Thalaiyasingam","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210089985"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7497000098228455,"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":0.7497000098228455,"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":0.11980000138282776,"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":0.08269999921321869,"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/closed-captioning","display_name":"Closed captioning","score":0.7838000059127808},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.7111999988555908},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6236000061035156},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5945000052452087},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5669999718666077},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49059998989105225},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4417000114917755},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4237000048160553},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4016999900341034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8044000267982483},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7838000059127808},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.7111999988555908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6431999802589417},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6236000061035156},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5945000052452087},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5669999718666077},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49059998989105225},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4417000114917755},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4237000048160553},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36340001225471497},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.35010001063346863},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.34940001368522644},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32839998602867126},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.31520000100135803},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.287200003862381},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2838999927043915},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.2750999927520752},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C60478076","wikidata":"https://www.wikidata.org/wiki/Q3036835","display_name":"Reference data","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228953","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":25,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2741631785","https://openalex.org/W2886641317","https://openalex.org/W2905544595","https://openalex.org/W2964211610","https://openalex.org/W3026458074","https://openalex.org/W3034585290","https://openalex.org/W3172514680","https://openalex.org/W3203247393","https://openalex.org/W4229027288","https://openalex.org/W4292828970","https://openalex.org/W4312729433","https://openalex.org/W4312825288","https://openalex.org/W4312933868","https://openalex.org/W4312940158","https://openalex.org/W4313172370","https://openalex.org/W4313594336","https://openalex.org/W4386071700","https://openalex.org/W4386076215","https://openalex.org/W4386076428","https://openalex.org/W4386273457","https://openalex.org/W4390873054","https://openalex.org/W4390873539","https://openalex.org/W4394625619","https://openalex.org/W4407056550"],"related_works":[],"abstract_inverted_index":{"Composed":[0],"Image":[1],"Retrieval":[2],"(CIR)":[3],"is":[4],"the":[5,19,24,67,75,82,93,112,169,180],"task":[6],"of":[7,69,77,114,171,182],"retrieving":[8],"images":[9],"matching":[10],"a":[11,16,41,47,90],"reference":[12,25,42],"image":[13,26,130,142,156],"augmented":[14],"with":[15,74],"text,":[17,45],"where":[18,97],"text":[20,144],"describes":[21],"changes":[22],"to":[23,60,179],"in":[27,85,92,120,153],"natural":[28],"language.":[29],"Traditionally,":[30],"models":[31,107,119],"designed":[32],"for":[33,124],"CIR":[34,70,94,125],"have":[35],"relied":[36],"on":[37,128,158],"triplet":[38,53],"data":[39,54,123],"containing":[40],"image,":[43],"reformulation":[44,137],"and":[46,117,143,160],"target":[48],"image.":[49],"However,":[50],"curating":[51],"such":[52],"often":[55],"necessitates":[56],"human":[57,98],"intervention,":[58],"leading":[59],"prohibitive":[61],"costs.":[62],"This":[63],"challenge":[64],"has":[65],"hindered":[66],"scalability":[68],"model":[71,176],"training":[72,95],"even":[73],"availability":[76],"abundant":[78],"unlabeled":[79],"data.":[80],"With":[81],"recent":[83],"advances":[84],"foundational":[86],"models,":[87],"we":[88,110,133,164],"advocate":[89],"shift":[91],"paradigm":[96],"annotations":[99],"can":[100],"be":[101],"efficiently":[102,121],"replaced":[103],"by":[104,167],"large":[105,115],"language":[106,118],"(LLMs).":[108],"Specifically,":[109],"demonstrate":[111,165],"capability":[113],"captioning":[116],"generating":[122],"only":[126],"relying":[127],"unannotated":[129],"collections.":[131],"Additionally,":[132],"introduce":[134],"an":[135],"embedding":[136],"architecture":[138],"that":[139,166],"effectively":[140],"combines":[141],"modalities.":[145],"Our":[146],"model,":[147],"named":[148],"InstructCIR,":[149],"outperforms":[150],"state-of-the-art":[151],"methods":[152],"zero-shot":[154,175],"composed":[155],"retrieval":[157],"CIRR":[159],"FashionIQ":[161],"datasets.":[162],"Furthermore,":[163],"increasing":[168],"amount":[170],"generated":[172],"data,":[173],"our":[174],"gets":[177],"closer":[178],"performance":[181],"supervised":[183],"baselines.":[184]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}