{"id":"https://openalex.org/W4402915471","doi":"https://doi.org/10.1109/icip51287.2024.10648023","title":"Zero-Shot Composed Image Retrieval Considering Query-Target Relationship Leveraging Masked Image-Text Pairs","display_name":"Zero-Shot Composed Image Retrieval Considering Query-Target Relationship Leveraging Masked Image-Text Pairs","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4402915471","doi":"https://doi.org/10.1109/icip51287.2024.10648023"},"language":"en","primary_location":{"id":"doi:10.1109/icip51287.2024.10648023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip51287.2024.10648023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","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/A5079657645","display_name":"Huaying Zhang","orcid":"https://orcid.org/0000-0003-1046-7168"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Huaying Zhang","raw_affiliation_strings":["Hokkaido University,Graduate School of Information Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Graduate School of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071840670","display_name":"Rintaro Yanagi","orcid":"https://orcid.org/0000-0003-0110-7208"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rintaro Yanagi","raw_affiliation_strings":["Hokkaido University,Graduate School of Information Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Graduate School of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002757875","display_name":"Ren Togo","orcid":"https://orcid.org/0000-0002-4474-3995"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ren Togo","raw_affiliation_strings":["Hokkaido University,Faculty of Information Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009032240","display_name":"Takahiro Ogawa","orcid":"https://orcid.org/0000-0001-5332-8112"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Ogawa","raw_affiliation_strings":["Hokkaido University,Faculty of Information Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":null,"display_name":"Miki Haseyama","orcid":null},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Miki Haseyama","raw_affiliation_strings":["Hokkaido University,Graduate School of Information Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Graduate School of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8676,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75005175,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2431","last_page":"2437"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.992900013923645,"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":0.992900013923645,"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":0.9909999966621399,"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":0.7619893550872803},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6637793779373169},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6536804437637329},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.602794349193573},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5775216817855835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45114773511886597},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4493291676044464},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40651702880859375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7619893550872803},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6637793779373169},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6536804437637329},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.602794349193573},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5775216817855835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45114773511886597},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4493291676044464},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40651702880859375},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip51287.2024.10648023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip51287.2024.10648023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","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":26,"referenced_works":["https://openalex.org/W2068669304","https://openalex.org/W2101498401","https://openalex.org/W2132551672","https://openalex.org/W2392997304","https://openalex.org/W2736809457","https://openalex.org/W2770409546","https://openalex.org/W2886641317","https://openalex.org/W2905544595","https://openalex.org/W2956018683","https://openalex.org/W2964211610","https://openalex.org/W3026458074","https://openalex.org/W3096034082","https://openalex.org/W3110536152","https://openalex.org/W3172514680","https://openalex.org/W3175684172","https://openalex.org/W3203247393","https://openalex.org/W4230405732","https://openalex.org/W4287367114","https://openalex.org/W4292828970","https://openalex.org/W4313172370","https://openalex.org/W4386071700","https://openalex.org/W4390873539","https://openalex.org/W6739531988","https://openalex.org/W6757817989","https://openalex.org/W6791353385","https://openalex.org/W6841755765"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,30,34,40,50,61,93,118,134],"novel":[4,94],"zero-shot":[5,95,131],"composed":[6],"image":[7,28,32,48,56],"retrieval":[8],"(CIR)":[9],"method":[10,97],"considering":[11],"the":[12,26,46,55,67,74,79,108,123,145,148],"query-target":[13,75,124],"relationship":[14,76],"by":[15],"masked":[16,103],"image-text":[17,104,110],"pairs.":[18,105],"The":[19],"objective":[20],"of":[21,147],"CIR":[22,96,132],"is":[23,99,127],"to":[24,44,53,65,77,83,115],"retrieve":[25],"target":[27],"using":[29,102,133],"query":[31,35,47],"and":[33,57,59],"text.":[36],"Existing":[37],"methods":[38],"use":[39,60],"textual":[41,80,136],"inversion":[42,81,137],"network":[43,82,138],"convert":[45],"into":[49],"pseudo":[51],"word":[52],"compose":[54],"text":[58],"pre-trained":[62],"visual-language":[63],"model":[64],"realize":[66],"retrieval.":[68,87],"However,":[69],"they":[70],"do":[71],"not":[72],"consider":[73],"train":[78],"acquire":[84],"information":[85],"for":[86,121],"In":[88],"this":[89],"paper,":[90],"we":[91],"propose":[92],"that":[98,112,129],"trained":[100],"end-to-end":[101],"By":[106],"exploiting":[107],"abundant":[109],"pairs":[111],"are":[113],"convenient":[114],"obtain":[116],"with":[117],"masking":[119],"strategy":[120],"learning":[122],"relationship,":[125],"it":[126],"expected":[128],"accurate":[130],"retrieval-focused":[135],"can":[139],"be":[140],"realized.":[141],"Experimental":[142],"results":[143],"show":[144],"effectiveness":[146],"proposed":[149],"method.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-16T09:24:06.705377","created_date":"2025-10-10T00:00:00"}