{"id":"https://openalex.org/W4296915201","doi":"https://doi.org/10.1109/tmm.2022.3208742","title":"Heterogeneous Feature Alignment and Fusion in Cross-Modal Augmented Space for Composed Image Retrieval","display_name":"Heterogeneous Feature Alignment and Fusion in Cross-Modal Augmented Space for Composed Image Retrieval","publication_year":2022,"publication_date":"2022-09-22","ids":{"openalex":"https://openalex.org/W4296915201","doi":"https://doi.org/10.1109/tmm.2022.3208742"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3208742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3208742","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/A5003815633","display_name":"Huaxin Pang","orcid":"https://orcid.org/0000-0003-4998-4576"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaxin Pang","raw_affiliation_strings":["Beijing Key Laboratory of Advanced Information Science and Network Technology, Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4998-4576","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Advanced Information Science and Network Technology, Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006854141","display_name":"Shikui Wei","orcid":"https://orcid.org/0000-0003-3803-9763"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shikui Wei","raw_affiliation_strings":["Beijing Key Laboratory of Advanced Information Science and Network Technology, Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3803-9763","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Advanced Information Science and Network Technology, Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021098663","display_name":"Gangjian Zhang","orcid":"https://orcid.org/0000-0003-1503-4513"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gangjian Zhang","raw_affiliation_strings":["Beijing Key Laboratory of Advanced Information Science and Network Technology, Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1503-4513","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Advanced Information Science and Network Technology, Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102006621","display_name":"Shiyin Zhang","orcid":"https://orcid.org/0000-0002-2128-0190"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyin Zhang","raw_affiliation_strings":["Beijing Key Laboratory of Advanced Information Science and Network Technology, Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2128-0190","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Advanced Information Science and Network Technology, Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101772154","display_name":"Shuang Qiu","orcid":"https://orcid.org/0000-0002-9769-5042"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Qiu","raw_affiliation_strings":["Beijing Key Laboratory of Advanced Information Science and Network Technology, Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9769-5042","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Advanced Information Science and Network Technology, Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100362745","display_name":"Yao Zhao","orcid":"https://orcid.org/0000-0002-8581-9554"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Zhao","raw_affiliation_strings":["Beijing Key Laboratory of Advanced Information Science and Network Technology, Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8581-9554","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Advanced Information Science and Network Technology, Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":1.1371,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.77713404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"25","issue":null,"first_page":"6446","last_page":"6457"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9998000264167786,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9965000152587891,"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":0.8694107532501221},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.7199609875679016},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6402245163917542},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6265629529953003},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.47897055745124817},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46131157875061035},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.43878450989723206},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4297836422920227},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4257253110408783},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41986143589019775},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4135298728942871},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38330310583114624},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35789620876312256}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8694107532501221},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.7199609875679016},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6402245163917542},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6265629529953003},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.47897055745124817},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46131157875061035},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.43878450989723206},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4297836422920227},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4257253110408783},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41986143589019775},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4135298728942871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38330310583114624},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35789620876312256},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2022.3208742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3208742","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/G184867666","display_name":null,"funder_award_id":"2017YFC1703503","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W1486702217","https://openalex.org/W1514535095","https://openalex.org/W1527575280","https://openalex.org/W1528802670","https://openalex.org/W1895577753","https://openalex.org/W1933349210","https://openalex.org/W1948251820","https://openalex.org/W1998808035","https://openalex.org/W2064675550","https://openalex.org/W2096733369","https://openalex.org/W2101498401","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2325939864","https://openalex.org/W2340690086","https://openalex.org/W2412393473","https://openalex.org/W2463565445","https://openalex.org/W2467281799","https://openalex.org/W2467570466","https://openalex.org/W2471768434","https://openalex.org/W2546696630","https://openalex.org/W2587372848","https://openalex.org/W2737766105","https://openalex.org/W2747635822","https://openalex.org/W2760103357","https://openalex.org/W2798951647","https://openalex.org/W2883311563","https://openalex.org/W2883672875","https://openalex.org/W2885402090","https://openalex.org/W2896263514","https://openalex.org/W2905544595","https://openalex.org/W2947448682","https://openalex.org/W2949197413","https://openalex.org/W2951529591","https://openalex.org/W2953037339","https://openalex.org/W2962926870","https://openalex.org/W2962933067","https://openalex.org/W2962964995","https://openalex.org/W2963040148","https://openalex.org/W2963113062","https://openalex.org/W2963150162","https://openalex.org/W2963176022","https://openalex.org/W2963180826","https://openalex.org/W2963383024","https://openalex.org/W2963389687","https://openalex.org/W2963656855","https://openalex.org/W2963907629","https://openalex.org/W2963910742","https://openalex.org/W2964067226","https://openalex.org/W2964138017","https://openalex.org/W2964196083","https://openalex.org/W2964211610","https://openalex.org/W2966715458","https://openalex.org/W2971157635","https://openalex.org/W2973233205","https://openalex.org/W2980088508","https://openalex.org/W2994818707","https://openalex.org/W2996478685","https://openalex.org/W2998356391","https://openalex.org/W3020827971","https://openalex.org/W3025297341","https://openalex.org/W3026458074","https://openalex.org/W3034585290","https://openalex.org/W3035552787","https://openalex.org/W3038703236","https://openalex.org/W3090449556","https://openalex.org/W3119510203","https://openalex.org/W3159583533","https://openalex.org/W4205474609","https://openalex.org/W4385245566","https://openalex.org/W6631516269","https://openalex.org/W6715144786","https://openalex.org/W6719057275","https://openalex.org/W6728881024","https://openalex.org/W6738893770","https://openalex.org/W6739901393","https://openalex.org/W6740863234","https://openalex.org/W6763623397","https://openalex.org/W6766904570","https://openalex.org/W6768730002","https://openalex.org/W6776721752","https://openalex.org/W6780783783"],"related_works":["https://openalex.org/W2172231696","https://openalex.org/W2089969684","https://openalex.org/W2002918846","https://openalex.org/W2503910294","https://openalex.org/W2393699422","https://openalex.org/W2384506582","https://openalex.org/W1658719554","https://openalex.org/W2168037874","https://openalex.org/W2135728080","https://openalex.org/W2105240677"],"abstract_inverted_index":{"Composed":[0],"image":[1,9,22,69,147],"retrieval":[2,96],"(CIR)":[3],"aims":[4],"at":[5],"fusing":[6],"a":[7,166],"reference":[8],"and":[10,33,51,65,70,93,118,135,150,154,187],"text":[11,71,92,116,151],"feedback":[12],"to":[13,20,74,79,114,142,190],"search":[14,29,34],"for":[15,173],"the":[16,27,35,57,62,108,121,127,156,160,184,199,204],"desired":[17],"images.":[18],"Compared":[19],"general":[21],"retrieval,":[23],"it":[24],"can":[25,124,182],"model":[26],"users'":[28],"intent":[30],"more":[31,38],"comprehensively":[32],"target":[36],"images":[37,94,119],"accurately,":[39],"which":[40,90,123,181],"has":[41],"significant":[42],"impacts":[43],"in":[44,120],"various":[45],"real-world":[46],"applications,":[47],"such":[48],"as":[49,95],"E-commerce":[50],"Internet":[52],"search.":[53],"However,":[54],"because":[55],"of":[56,67,159],"existing":[58,205],"heterogeneous":[59,128],"semantic":[60,194],"gap,":[61],"synthetic":[63],"understanding":[64],"fusion":[66],"both":[68],"are":[72,140],"difficult":[73,82],"implement.":[75],"In":[76],"this":[77,81],"work,":[78],"tackle":[80],"problem,":[83],"we":[84,106,164],"propose":[85],"an":[86,192],"end-to-end":[87],"framework":[88,99],"MCR,":[89],"uses":[91],"queries.":[97],"The":[98,130],"mainly":[100],"includes":[101],"four":[102],"pivotal":[103],"modules.":[104],"Specifically,":[105],"introduce":[107],"Relative":[109],"Caption-aware":[110],"Consistency":[111],"(RCC)":[112],"constraint":[113],"align":[115],"pieces":[117],"database,":[122],"effectually":[125],"bridge":[126],"gap.":[129],"Multi-modal":[131],"Complementary":[132],"Fusion":[133],"(MCF)":[134],"Cross-modal":[136],"Guided":[137],"Pooling":[138],"(CGP)":[139],"constructed":[141],"mine":[143],"multiple":[144],"interactions":[145],"between":[146],"local":[148],"features":[149,153,186],"word":[152],"learn":[155],"complementary":[157],"representation":[158],"composed":[161],"query.":[162],"Furthermore,":[163],"develop":[165],"plug-and-play":[167],"Weak-text":[168],"Semantic":[169],"Augment":[170],"(WSA)":[171],"module":[172],"datasets":[174],"with":[175],"short":[176],"or":[177],"incomplete":[178],"query":[179],"texts,":[180],"supplement":[183],"weak-text":[185],"is":[188],"conducive":[189],"modeling":[191],"augmented":[193],"space.":[195],"Extensive":[196],"experiments":[197],"demonstrate":[198],"practical":[200],"superior":[201],"performance":[202],"over":[203],"state-of-the-art":[206],"empirical":[207],"algorithms":[208],"on":[209],"several":[210],"benchmarks.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}