{"id":"https://openalex.org/W7124919030","doi":"https://doi.org/10.1109/cbmi66578.2025.11339329","title":"Text-Oriented Image Query Representation for Zero-Shot Composed Image Retrieval","display_name":"Text-Oriented Image Query Representation for Zero-Shot Composed Image Retrieval","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W7124919030","doi":"https://doi.org/10.1109/cbmi66578.2025.11339329"},"language":null,"primary_location":{"id":"doi:10.1109/cbmi66578.2025.11339329","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","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/A5072414358","display_name":"Pavan Kartheek Rachabathuni","orcid":null},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Pavan Kartheek Rachabathuni","raw_affiliation_strings":["University of Florence - MICC,Florence,Italy"],"affiliations":[{"raw_affiliation_string":"University of Florence - MICC,Florence,Italy","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057939329","display_name":"Andrea Ciamarra","orcid":"https://orcid.org/0000-0001-7053-0830"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Ciamarra","raw_affiliation_strings":["CNIT Florence,Florence,Italy"],"affiliations":[{"raw_affiliation_string":"CNIT Florence,Florence,Italy","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123437188","display_name":"Roberto Caldelli","orcid":null},"institutions":[{"id":"https://openalex.org/I4210132817","display_name":"Mercatorum University","ror":"https://ror.org/03znjxt55","country_code":"IT","type":"education","lineage":["https://openalex.org/I4210132817"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Roberto Caldelli","raw_affiliation_strings":["CNIT Florence and Universitas Mercatorum,Rome,Italy"],"affiliations":[{"raw_affiliation_string":"CNIT Florence and Universitas Mercatorum,Rome,Italy","institution_ids":["https://openalex.org/I4210132817"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108651472","display_name":"Marco Bertini","orcid":null},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Bertini","raw_affiliation_strings":["University of Florence - MICC,Florence,Italy"],"affiliations":[{"raw_affiliation_string":"University of Florence - MICC,Florence,Italy","institution_ids":["https://openalex.org/I45084792"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072414358"],"corresponding_institution_ids":["https://openalex.org/I45084792"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.70014503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4496000111103058,"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":0.4496000111103058,"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":0.3944000005722046,"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":0.09510000050067902,"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/query-expansion","display_name":"Query expansion","score":0.5845999717712402},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5809999704360962},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.558899998664856},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.512499988079071},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5103999972343445},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48590001463890076},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.4830000102519989},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4652000069618225},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.43639999628067017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8118000030517578},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.5845999717712402},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5809999704360962},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.558899998664856},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.512499988079071},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5103999972343445},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48590001463890076},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48069998621940613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48010000586509705},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4652000069618225},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.43639999628067017},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.41499999165534973},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.3716000020503998},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.35260000824928284},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C2778816267","wikidata":"https://www.wikidata.org/wiki/Q21015578","display_name":"Semantic query","level":4,"score":0.30320000648498535},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2874000072479248},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2815000116825104},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.2768000066280365},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cbmi66578.2025.11339329","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","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":31,"referenced_works":["https://openalex.org/W2045456846","https://openalex.org/W2054743810","https://openalex.org/W2081059587","https://openalex.org/W2145344560","https://openalex.org/W2765392594","https://openalex.org/W2766280096","https://openalex.org/W2891999386","https://openalex.org/W2905544595","https://openalex.org/W3092932168","https://openalex.org/W3171668871","https://openalex.org/W3172514680","https://openalex.org/W3203247393","https://openalex.org/W3206012133","https://openalex.org/W3206569427","https://openalex.org/W3207731638","https://openalex.org/W4304083944","https://openalex.org/W4304091775","https://openalex.org/W4312825288","https://openalex.org/W4313172370","https://openalex.org/W4386071700","https://openalex.org/W4386290297","https://openalex.org/W4386501573","https://openalex.org/W4390873539","https://openalex.org/W4394625619","https://openalex.org/W4399251441","https://openalex.org/W4400530983","https://openalex.org/W4402673375","https://openalex.org/W4402716321","https://openalex.org/W4402727158","https://openalex.org/W4403792412","https://openalex.org/W4412722575"],"related_works":[],"abstract_inverted_index":{"Zero-Shot":[0],"Composed":[1],"Image":[2],"Retrieval":[3],"(ZS-CIR)":[4],"is":[5,87,131],"the":[6,52,93,99,112,116,121,139,146,150,153],"task":[7],"of":[8,115],"retrieving":[9],"a":[10,15,19,23,30,43,65,70,125,156,190],"target":[11,147],"image":[12,21],"based":[13,119],"on":[14,120,172],"query":[16,45,127],"that":[17,68,183],"combines":[18],"reference":[20],"with":[22,145,159],"textual":[24,40],"description":[25],"specifying":[26],"desired":[27],"modifications":[28],"in":[29,107],"zero-shot":[31],"setting.":[32],"Existing":[33],"ZS-CIR":[34,187],"models":[35],"typically":[36],"fuse":[37],"visual":[38,117],"and":[39,75,98,179],"modalities":[41],"into":[42],"single":[44],"representation,":[46],"but":[47],"often":[48],"struggle":[49],"to":[50,79,142,165,181],"capture":[51],"fine-grained":[53],"distinctions":[54],"essential":[55],"for":[56,193],"accurate":[57],"retrieval.":[58,195],"In":[59],"this":[60],"paper,":[61],"we":[62],"present":[63],"TEOZCIR,":[64],"transformer-based":[66],"model":[67,86,154],"introduces":[69],"balanced":[71,126],"semantic":[72,113],"fusion":[73],"module":[74],"an":[76],"enhancement":[77],"mechanism":[78],"more":[80],"effectively":[81],"integrate":[82],"multimodal":[83,194],"information.":[84],"The":[85],"built":[88],"around":[89],"two":[90],"core":[91],"components:":[92],"Text-Aware":[94],"Query":[95,100],"Combiner":[96],"(TAQC)":[97],"Enhancer":[101],"Network":[102],"(QENet).":[103],"These":[104],"components":[105],"operate":[106],"tandem:":[108],"TAQC":[109],"dynamically":[110],"adjusts":[111],"contributions":[114],"context":[118],"input":[122],"text,":[123],"generating":[124],"representation.":[128],"This":[129],"representation":[130],"then":[132],"further":[133],"refined":[134],"by":[135],"QENet,":[136],"which":[137],"enhances":[138],"fused":[140],"features":[141],"better":[143],"align":[144],"image.":[148],"Throughout":[149],"entire":[151],"process,":[152],"maintains":[155],"lightweight":[157],"architecture":[158],"significantly":[160,185],"fewer":[161],"trainable":[162],"parameters":[163],"compared":[164],"conventional":[166],"training-based":[167],"methods.":[168],"Experiments":[169],"carried":[170],"out":[171],"three":[173],"benchmark":[174],"datasets":[175],"CIRR,":[176],"Fashion":[177],"IQ,":[178],"CIRCO":[180],"demonstrate":[182],"TEOZCIR":[184],"improves":[186],"performance,":[188],"setting":[189],"new":[191],"bench-mark":[192]},"counts_by_year":[],"updated_date":"2026-01-22T23:29:09.771500","created_date":"2026-01-21T00:00:00"}