{"id":"https://openalex.org/W4313855701","doi":"https://doi.org/10.1109/tmm.2023.3235495","title":"Multi-Modal Transformer With Global-Local Alignment for Composed Query Image Retrieval","display_name":"Multi-Modal Transformer With Global-Local Alignment for Composed Query Image Retrieval","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4313855701","doi":"https://doi.org/10.1109/tmm.2023.3235495"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3235495","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3235495","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/A5014129038","display_name":"Yahui Xu","orcid":"https://orcid.org/0000-0002-1123-6129"},"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":"Yahui Xu","raw_affiliation_strings":["Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","Guoqing Wang are with the Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-1123-6129","affiliations":[{"raw_affiliation_string":"Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Guoqing Wang are with the Center for Future Media and 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/A5024408423","display_name":"Yi Bin","orcid":"https://orcid.org/0000-0001-9714-8738"},"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":"Yi Bin","raw_affiliation_strings":["Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","Guoqing Wang are with the Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-9714-8738","affiliations":[{"raw_affiliation_string":"Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Guoqing Wang are with the Center for Future Media and 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/A5060342584","display_name":"Jiwei Wei","orcid":"https://orcid.org/0000-0003-3912-1742"},"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":"Jiwei Wei","raw_affiliation_strings":["Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","Guoqing Wang are with the Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-3912-1742","affiliations":[{"raw_affiliation_string":"Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Guoqing Wang are with the Center for Future Media and 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/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"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":"Yang Yang","raw_affiliation_strings":["Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","Institute of Electronic and Information Engineering, University of Electronic Science and Technology of China, Guangdong, China","Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-5070-4511","affiliations":[{"raw_affiliation_string":"Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Institute of Electronic and Information Engineering, University of Electronic Science and Technology of China, Guangdong, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Center for Future Media, and the 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/A5100334018","display_name":"Guoqing Wang","orcid":"https://orcid.org/0000-0002-3938-5994"},"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":"Guoqing Wang","raw_affiliation_strings":["Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","Guoqing Wang are with the Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-3938-5994","affiliations":[{"raw_affiliation_string":"Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Guoqing Wang are with the Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"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"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["Center for Future Multimedia and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","the Center for Future Multimedia and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"Center for Future Multimedia and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"the Center for Future Multimedia and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.779,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.9651932,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"25","issue":null,"first_page":"8346","last_page":"8357"},"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":0.9988999962806702,"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":0.9988999962806702,"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":0.998199999332428,"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":0.9968000054359436,"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":0.8449962139129639},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6156929731369019},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5566325783729553},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5486956834793091},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49598273634910583},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.48144811391830444},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4682164192199707},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3689890503883362},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36418554186820984},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2643159031867981},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2535565495491028}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8449962139129639},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6156929731369019},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5566325783729553},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5486956834793091},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49598273634910583},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.48144811391830444},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4682164192199707},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3689890503883362},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36418554186820984},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2643159031867981},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2535565495491028},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3235495","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3235495","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":[{"id":"https://openalex.org/G2464018058","display_name":null,"funder_award_id":"U20B2063","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5181088096","display_name":null,"funder_award_id":"2021M690027","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G6930405597","display_name":null,"funder_award_id":"BX2021055","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G8836073055","display_name":null,"funder_award_id":"62102070","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"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2064675550","https://openalex.org/W2103220603","https://openalex.org/W2194775991","https://openalex.org/W2656999302","https://openalex.org/W2752667240","https://openalex.org/W2752674409","https://openalex.org/W2765440071","https://openalex.org/W2766724094","https://openalex.org/W2803620531","https://openalex.org/W2804847616","https://openalex.org/W2905544595","https://openalex.org/W2908230750","https://openalex.org/W2955147859","https://openalex.org/W2962946486","https://openalex.org/W2963163009","https://openalex.org/W2964211610","https://openalex.org/W2966218308","https://openalex.org/W2970231061","https://openalex.org/W2971061988","https://openalex.org/W2979667596","https://openalex.org/W2981448404","https://openalex.org/W2998315347","https://openalex.org/W3003460937","https://openalex.org/W3025297341","https://openalex.org/W3026458074","https://openalex.org/W3034585290","https://openalex.org/W3034603197","https://openalex.org/W3035212740","https://openalex.org/W3038703236","https://openalex.org/W3092962760","https://openalex.org/W3112077297","https://openalex.org/W3119510203","https://openalex.org/W3134272453","https://openalex.org/W3138516171","https://openalex.org/W3172514680","https://openalex.org/W3175684172","https://openalex.org/W3176909828","https://openalex.org/W3180476551","https://openalex.org/W3186567887","https://openalex.org/W3187176672","https://openalex.org/W3187240237","https://openalex.org/W3203247393","https://openalex.org/W3205173298","https://openalex.org/W3206012133","https://openalex.org/W3206128852","https://openalex.org/W3206569427","https://openalex.org/W3214466318","https://openalex.org/W4206516739","https://openalex.org/W4214597499","https://openalex.org/W4226094317","https://openalex.org/W4292787334","https://openalex.org/W4304091961","https://openalex.org/W4304092541","https://openalex.org/W4306833423","https://openalex.org/W4312940158","https://openalex.org/W6631190155","https://openalex.org/W6739531988","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6780062628","https://openalex.org/W6780783783","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6789753369","https://openalex.org/W6803794721","https://openalex.org/W6804198819","https://openalex.org/W6810496820"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W4390516098","https://openalex.org/W2560191017","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2183306018","https://openalex.org/W2549990292","https://openalex.org/W2345479200","https://openalex.org/W2348892528","https://openalex.org/W4205302943"],"abstract_inverted_index":{"In":[0,72],"this":[1,36,163],"paper,":[2],"we":[3,146,171,212],"study":[4],"the":[5,14,19,27,48,66,80,111,116,124,136,140,156,160,168,180,186,190,201,209,221,224,228,235,238,246,251,262],"composed":[6,20,49,81,157,202,225],"query":[7,50,158,203,226],"image":[8,16,25,34,53,68],"retrieval,":[9,35],"which":[10,153],"aims":[11],"at":[12,204],"retrieving":[13],"target":[15,52,229],"similar":[17],"to":[18,74,166,177,198,219,248],"query,":[21,82],"i.e.,":[22],"a":[23,55,104,148,173],"reference":[24,67],"and":[26,51,69,97,101,227],"desired":[28],"modification":[29,70],"text.":[30,71],"Compared":[31],"with":[32,159],"conventional":[33],"task":[37],"is":[38,196],"more":[39],"challenging":[40],"as":[41],"it":[42],"not":[43,232],"only":[44,233],"requires":[45],"precisely":[46],"aligning":[47],"in":[54,119,237],"common":[56],"embedding":[57,241],"space,":[58],"but":[59,243],"also":[60,244],"simultaneously":[61],"extracting":[62],"related":[63,77],"information":[64,78],"from":[65,79],"order":[73],"properly":[75],"extract":[76],"existing":[83],"methods":[84],"usually":[85],"embed":[86],"vision-language":[87,125,181],"inputs":[88],"using":[89],"different":[90],"feature":[91,120],"encoders,":[92],"e.g.,":[93],"CNN":[94],"for":[95,99,109,162],"images":[96],"LSTM/BERT":[98],"text,":[100],"then":[102],"employ":[103],"complicated":[105,130,187],"manually-designed":[106],"composition":[107,131,188],"module":[108,218],"learning":[110],"joint":[112,240],"image-text":[113],"representation.":[114],"However,":[115],"architecture":[117,169,176],"discrepancy":[118],"encoders":[121],"would":[122],"restrict":[123],"plenitudinous":[126],"interaction.":[127],"Meanwhile,":[128,183],"certain":[129],"designs":[132],"might":[133],"significantly":[134],"hamper":[135],"generalization":[137],"ability":[138],"of":[139,185,264],"model.":[141],"To":[142],"tackle":[143],"these":[144],"problems,":[145],"propose":[147],"new":[149],"framework":[150],"termed":[151],"ComqueryFormer,":[152],"effectively":[154],"processes":[155],"Transformer":[161],"task.":[164],"Specifically,":[165],"eliminate":[167],"discrepancy,":[170],"leverage":[172],"unified":[174],"transformer-based":[175],"homogeneously":[178],"encode":[179],"inputs.":[182],"instead":[184],"module,":[189],"neat":[191],"yet":[192],"effective":[193],"cross-modal":[194],"transformer":[195],"adopted":[197],"hierarchically":[199],"fuse":[200],"various":[205],"vision":[206],"scales.":[207],"On":[208],"other":[210],"hand,":[211],"introduce":[213],"an":[214],"efficient":[215],"global-local":[216],"alignment":[217],"narrow":[220],"distance":[222],"between":[223],"image.":[230],"It":[231],"considers":[234],"divergence":[236],"global":[239],"space":[242],"forces":[245],"model":[247],"focus":[249],"on":[250,257],"local":[252],"detail":[253],"differences.":[254],"Extensive":[255],"experiments":[256],"three":[258],"real-world":[259],"datasets":[260],"demonstrate":[261],"superiority":[263],"our":[265],"ComqueryFormer.":[266],"Our":[267],"code":[268],"can":[269],"be":[270],"found":[271],"at:":[272],"<uri":[273],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[274],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/uestc-xyh/ComqueryFormer</uri>":[275],".":[276]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":11}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}