{"id":"https://openalex.org/W4399881520","doi":"https://doi.org/10.1109/tmm.2024.3417694","title":"Align and Retrieve: Composition and Decomposition Learning in Image Retrieval With Text Feedback","display_name":"Align and Retrieve: Composition and Decomposition Learning in Image Retrieval With Text Feedback","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4399881520","doi":"https://doi.org/10.1109/tmm.2024.3417694"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3417694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3417694","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"],"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"]}]},{"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/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yi Bin","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-9714-8738","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"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"],"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"]}]},{"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 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 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"],"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"]}]},{"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"]}],"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"],"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"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.651,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84108559,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"26","issue":null,"first_page":"9936","last_page":"9948"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9975000023841858,"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":0.9975000023841858,"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":0.9812999963760376,"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":0.960099995136261,"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":0.8591813445091248},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6538000702857971},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6474495530128479},{"id":"https://openalex.org/keywords/relevance-feedback","display_name":"Relevance feedback","score":0.46673640608787537},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.4531269073486328},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42584142088890076},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35693708062171936},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3566718101501465}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8591813445091248},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6538000702857971},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6474495530128479},{"id":"https://openalex.org/C2779532271","wikidata":"https://www.wikidata.org/wiki/Q445558","display_name":"Relevance feedback","level":4,"score":0.46673640608787537},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.4531269073486328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42584142088890076},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35693708062171936},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3566718101501465},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3417694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3417694","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/G1294623083","display_name":null,"funder_award_id":"62220106008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2037020671","display_name":null,"funder_award_id":"62102069","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"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/G3023062769","display_name":null,"funder_award_id":"U23B2011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G591136627","display_name":null,"funder_award_id":"62306067","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W1528802670","https://openalex.org/W1902237438","https://openalex.org/W2019370496","https://openalex.org/W2064675550","https://openalex.org/W2105482032","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2752674409","https://openalex.org/W2752782242","https://openalex.org/W2760103357","https://openalex.org/W2765440071","https://openalex.org/W2787802257","https://openalex.org/W2892071519","https://openalex.org/W2903659352","https://openalex.org/W2905544595","https://openalex.org/W2913950831","https://openalex.org/W2952866723","https://openalex.org/W2962858109","https://openalex.org/W2963091558","https://openalex.org/W2963201326","https://openalex.org/W2963328724","https://openalex.org/W2963588253","https://openalex.org/W2964211610","https://openalex.org/W2966683369","https://openalex.org/W2986670728","https://openalex.org/W3026458074","https://openalex.org/W3034585290","https://openalex.org/W3035524453","https://openalex.org/W3038703236","https://openalex.org/W3092962760","https://openalex.org/W3134272453","https://openalex.org/W3138366398","https://openalex.org/W3169472988","https://openalex.org/W3172514680","https://openalex.org/W3173220247","https://openalex.org/W3175684172","https://openalex.org/W3176278386","https://openalex.org/W3176909828","https://openalex.org/W3194557739","https://openalex.org/W3195963939","https://openalex.org/W3203247393","https://openalex.org/W3205173298","https://openalex.org/W3206012133","https://openalex.org/W3206569427","https://openalex.org/W3206597437","https://openalex.org/W4206516739","https://openalex.org/W4224929299","https://openalex.org/W4289752563","https://openalex.org/W4296915201","https://openalex.org/W4312825288","https://openalex.org/W4312940158","https://openalex.org/W4313855701","https://openalex.org/W4320008746","https://openalex.org/W4360103755","https://openalex.org/W4378505291","https://openalex.org/W4379539165","https://openalex.org/W4381804476","https://openalex.org/W4385245566","https://openalex.org/W4385895960","https://openalex.org/W4385934203","https://openalex.org/W4385965620","https://openalex.org/W4386075952","https://openalex.org/W4386273457","https://openalex.org/W4393149123","https://openalex.org/W4394625619","https://openalex.org/W6631190155","https://openalex.org/W6682137061","https://openalex.org/W6715144786","https://openalex.org/W6738893770","https://openalex.org/W6747837047","https://openalex.org/W6751039726","https://openalex.org/W6780783783","https://openalex.org/W6791353385","https://openalex.org/W6810496820","https://openalex.org/W6811013733","https://openalex.org/W6849177959","https://openalex.org/W6850956941","https://openalex.org/W6852548462","https://openalex.org/W6852813590","https://openalex.org/W6855856646","https://openalex.org/W6857730641"],"related_works":["https://openalex.org/W1606474234","https://openalex.org/W2034539438","https://openalex.org/W2124645781","https://openalex.org/W2184057774","https://openalex.org/W2140331143","https://openalex.org/W2543381692","https://openalex.org/W1975659822","https://openalex.org/W3087943932","https://openalex.org/W2349022781","https://openalex.org/W2168747791"],"abstract_inverted_index":{"We":[0],"study":[1],"the":[2,21,33,47,50,54,58,69,73,76,82,87,124,128,138,153,157,169,173,185,188,199,209,213,237,247,250],"task":[3],"of":[4,72,249],"image":[5,13,162,175,201,215],"retrieval":[6],"with":[7,111,216],"text":[8,16,178,205],"feedback,":[9],"where":[10],"a":[11,112,144,164,180,224],"reference":[12,97,174],"and":[14,40,53,101,115,160,176,191,204],"modification":[15,99,177],"are":[17],"composed":[18,51,158],"to":[19,45,84,131,151,183,207,232],"retrieve":[20],"desired":[22],"target":[23,55,102,161,192,200,214],"image.":[24,56,103,193],"To":[25],"accomplish":[26],"this":[27,105],"goal,":[28],"existing":[29,91],"methods":[30,122],"always":[31],"get":[32],"multimodal":[34,59,78,134],"representations":[35],"through":[36],"different":[37,43],"feature":[38,129],"encoders":[39,130],"then":[41],"adopt":[42],"strategies":[44],"model":[46],"correlation":[48,90,140,155,186,211],"between":[49,156,187,212],"inputs":[52,79,159],"However,":[57],"query":[60,218],"brings":[61],"more":[62,145],"challenges":[63],"as":[64],"it":[65],"requires":[66],"not":[67],"only":[68],"synergistic":[70],"understanding":[71],"semantics":[74],"from":[75],"heterogeneous":[77],"but":[80],"also":[81],"ability":[83],"accurately":[85],"build":[86],"underlying":[88,210],"semantic":[89],"in":[92,127,143,163,236],"each":[93,217,234],"inputs-target":[94],"triplet,":[95],"i.e.,":[96],"image,":[98],"text,":[100],"In":[104],"paper,":[106],"we":[107,149],"tackle":[108],"these":[109],"issues":[110],"novel":[113,165],"Align":[114],"Retrieve":[116],"(AlRet)":[117],"framework.":[118],"First,":[119],"our":[120],"proposed":[121,251],"employ":[123],"contrastive":[125],"loss":[126],"learn":[132,152,184],"meaningful":[133],"representation":[135,182,190],"while":[136],"making":[137],"subsequent":[139],"modeling":[141],"process":[142],"harmonious":[146],"space.":[147],"Then":[148],"propose":[150],"accurate":[154],"composition-and-decomposition":[166,221],"paradigm.":[167],"Specifically,":[168],"composition":[170],"network":[171,196],"couples":[172],"into":[179,202],"joint":[181,189],"The":[194,220],"decomposition":[195],"conversely":[197],"decouples":[198],"visual":[203],"subspaces":[206],"exploit":[208],"element.":[219],"paradigm":[222],"forms":[223],"closed":[225],"loop,":[226],"which":[227],"can":[228],"be":[229],"optimized":[230],"simultaneously":[231],"promote":[233],"other":[235],"performance.":[238],"Massive":[239],"comparison":[240],"experiments":[241],"on":[242],"three":[243],"real-world":[244],"datasets":[245],"confirm":[246],"effectiveness":[248],"method.":[252]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}