{"id":"https://openalex.org/W4390724303","doi":"https://doi.org/10.1145/3639469","title":"Cross-Modal Attention Preservation with Self-Contrastive Learning for Composed Query-Based Image Retrieval","display_name":"Cross-Modal Attention Preservation with Self-Contrastive Learning for Composed Query-Based Image Retrieval","publication_year":2024,"publication_date":"2024-01-09","ids":{"openalex":"https://openalex.org/W4390724303","doi":"https://doi.org/10.1145/3639469"},"language":"en","primary_location":{"id":"doi:10.1145/3639469","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3639469","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5043867916","display_name":"Shenshen Li","orcid":"https://orcid.org/0000-0002-6340-012X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenshen Li","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-6340-012X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009074046","display_name":"Xing Xu","orcid":"https://orcid.org/0000-0001-5685-3123"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-5685-3123","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101786662","display_name":"Xun Jiang","orcid":"https://orcid.org/0000-0003-2209-651X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Jiang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-2209-651X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074492050","display_name":"Fumin Shen","orcid":"https://orcid.org/0000-0001-7303-3231"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fumin Shen","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-7303-3231","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025554387","display_name":"Zhe Sun","orcid":"https://orcid.org/0000-0002-6531-0769"},"institutions":[{"id":"https://openalex.org/I4210145596","display_name":"Juntendo University Hospital","ror":"https://ror.org/04g0m2d49","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I4210145596"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhe Sun","raw_affiliation_strings":["Juntendo University, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-6531-0769","affiliations":[{"raw_affiliation_string":"Juntendo University, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018676117","display_name":"Andrzej Cichocki","orcid":"https://orcid.org/0000-0002-8364-7226"},"institutions":[{"id":"https://openalex.org/I66083562","display_name":"Systems Research Institute","ror":"https://ror.org/0111cp837","country_code":"PL","type":"facility","lineage":["https://openalex.org/I66083562","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Andrzej Cichocki","raw_affiliation_strings":["Systems Research Institute of Polish Academy of Science, Warszawa, Poland and Tensor Learning Lab, Riken AIP, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-8364-7226","affiliations":[{"raw_affiliation_string":"Systems Research Institute of Polish Academy of Science, Warszawa, Poland and Tensor Learning Lab, Riken AIP, Tokyo, Japan","institution_ids":["https://openalex.org/I66083562"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4743,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.93540739,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"20","issue":"6","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"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":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"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":0.6860691905021667},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6424775719642639},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4951535761356354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4600546061992645},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.42313048243522644},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.0578363835811615}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6860691905021667},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6424775719642639},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4951535761356354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4600546061992645},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42313048243522644},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0578363835811615},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3639469","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3639469","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4510122299","display_name":"\u9762\u5411\u81ea\u7136\u8bed\u53e5\u67e5\u8be2\u7684\u591a\u6a21\u6001\u6570\u636e\u68c0\u7d22\u7814\u7a76","funder_award_id":"62072080","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4765907288","display_name":null,"funder_award_id":"61976049","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4782833057","display_name":null,"funder_award_id":"62222203, 61976049, and 62072080","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5347999826","display_name":null,"funder_award_id":"62222203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1528802670","https://openalex.org/W2064675550","https://openalex.org/W2096733369","https://openalex.org/W2117539524","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2560674852","https://openalex.org/W2765440071","https://openalex.org/W2905544595","https://openalex.org/W2962964995","https://openalex.org/W2964211610","https://openalex.org/W2969985801","https://openalex.org/W2985951359","https://openalex.org/W2988772405","https://openalex.org/W3019359265","https://openalex.org/W3026458074","https://openalex.org/W3034585290","https://openalex.org/W3049148844","https://openalex.org/W3119510203","https://openalex.org/W3154902219","https://openalex.org/W3172514680","https://openalex.org/W3174873881","https://openalex.org/W3175684172","https://openalex.org/W3176909828","https://openalex.org/W3193057479","https://openalex.org/W3203247393","https://openalex.org/W3206128852","https://openalex.org/W3206569427","https://openalex.org/W3206868111","https://openalex.org/W4205488143","https://openalex.org/W4212774754","https://openalex.org/W4214819138","https://openalex.org/W4214920941","https://openalex.org/W4221141095","https://openalex.org/W4221148695","https://openalex.org/W4225957036","https://openalex.org/W4280608816","https://openalex.org/W4286233488","https://openalex.org/W4294691145","https://openalex.org/W4297808394","https://openalex.org/W4309136123","https://openalex.org/W4309764765","https://openalex.org/W4312729433","https://openalex.org/W4312825288","https://openalex.org/W4312940158","https://openalex.org/W4321372711","https://openalex.org/W4360103755","https://openalex.org/W4385486155","https://openalex.org/W4386038408","https://openalex.org/W4387968696","https://openalex.org/W4387969779"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"In":[0],"this":[1,114],"article,":[2],"we":[3,92,116,133],"study":[4],"the":[5,19,41,47,59,65,71,95,100,109,136,150,174,178,181,185,209,215],"challenging":[6,51],"cross-modal":[7,43],"image":[8,61,155],"retrieval":[9,45,111],"task,":[10,46],"Composed":[11],"Query-Based":[12],"Image":[13],"Retrieval":[14],"(CQBIR)":[15],",":[16],"in":[17],"which":[18,146],"query":[20,26],"is":[21,49,225],"not":[22],"a":[23,28,32,36,88,118],"single":[24],"text":[25],"but":[27],"composed":[29],"query,":[30],"i.e.,":[31,196],"reference":[33],"image,":[34],"and":[35,57,81,84,199],"modification":[37],"text.":[38],"Compared":[39],"with":[40,184],"conventional":[42,160],"image-text":[44],"CQBIR":[48,194],"more":[50],"as":[52],"it":[53,86],"requires":[54],"properly":[55],"preserving":[56],"modifying":[58],"specific":[60],"region":[62],"according":[63],"to":[64,139,148,172],"multi-level":[66],"semantic":[67,144],"information":[68,83],"learned":[69,98],"from":[70,159,176],"multi-modal":[72],"query.":[73],"Most":[74],"recent":[75],"works":[76],"focus":[77],"on":[78,190,213],"extracting":[79],"preserved":[80,96,170,182],"modified":[82,105,186],"compositing":[85],"into":[87,168],"unified":[89],"representation.":[90],"However,":[91],"observe":[93],"that":[94,202],"regions":[97],"by":[99],"existing":[101],"methods":[102,212],"contain":[103],"redundant":[104],"information,":[106,145,171],"inevitably":[107],"degrading":[108],"overall":[110],"performance.":[112],"To":[113],"end,":[115],"propose":[117],"novel":[119],"method":[120,164,206,224],"termed":[121],"C":[122],"ross-":[123],"M":[124],"odal":[125],"A":[126],"ttention":[127],"P":[128],"reservation":[129],"(CMAP)":[130],".":[131],"Specifically,":[132],"first":[134],"leverage":[135],"cross-level":[137],"interaction":[138],"fully":[140],"account":[141],"for":[142,153,180],"multi-granular":[143],"aims":[147],"supplement":[149],"high-level":[151],"semantics":[152],"effective":[154],"retrieval.":[156],"Furthermore,":[157],"different":[158],"contrastive":[161],"learning,":[162],"our":[163,203,222],"introduces":[165],"self-contrastive":[166],"learning":[167,169],"prevent":[173],"model":[175],"confusing":[177],"attention":[179],"part":[183],"part.":[187],"Extensive":[188],"experiments":[189],"three":[191],"widely":[192],"used":[193],"datasets,":[195],"FashionIQ,":[197],"Shoes,":[198],"Fashion200k,":[200],"demonstrate":[201],"proposed":[204],"CMAP":[205,223],"significantly":[207],"outperforms":[208],"current":[210],"state-of-the-art":[211],"all":[214],"datasets.":[216],"The":[217],"anonymous":[218],"implementation":[219],"code":[220],"of":[221],"available":[226],"at":[227],"https://github.com/CFM-MSG/Code_CMAP.":[228]},"counts_by_year":[{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}