{"id":"https://openalex.org/W4375801927","doi":"https://doi.org/10.1109/tmm.2023.3273466","title":"Enhance Composed Image Retrieval via Multi-Level Collaborative Localization and Semantic Activeness Perception","display_name":"Enhance Composed Image Retrieval via Multi-Level Collaborative Localization and Semantic Activeness Perception","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375801927","doi":"https://doi.org/10.1109/tmm.2023.3273466"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3273466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3273466","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/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":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1503-4513","affiliations":[{"raw_affiliation_string":"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":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3803-9763","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","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":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4998-4576","affiliations":[{"raw_affiliation_string":"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/I9086337","display_name":"Taiyuan University of Technology","ror":"https://ror.org/03kv08d37","country_code":"CN","type":"education","lineage":["https://openalex.org/I9086337"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Qiu","raw_affiliation_strings":["College of Data Science, Taiyuan University of Technology, Taiyuan, China"],"raw_orcid":"https://orcid.org/0000-0002-9769-5042","affiliations":[{"raw_affiliation_string":"College of Data Science, Taiyuan University of Technology, Taiyuan, China","institution_ids":["https://openalex.org/I9086337"]}]},{"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":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8581-9554","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8773,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.70894248,"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":"916","last_page":"928"},"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":0.9998000264167786,"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"}},"topics":[{"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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":0.9984999895095825,"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":0.8405367136001587},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6688494086265564},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5934438705444336},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5585181713104248},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5374150276184082},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5341160893440247},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5239375233650208},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5215684771537781},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4697665870189667},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.45718806982040405},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.45126840472221375},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.4104456305503845},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3602716326713562},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3405948579311371},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0718097984790802}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8405367136001587},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6688494086265564},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5934438705444336},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5585181713104248},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5374150276184082},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5341160893440247},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5239375233650208},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5215684771537781},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4697665870189667},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.45718806982040405},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.45126840472221375},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.4104456305503845},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3602716326713562},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3405948579311371},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0718097984790802},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3273466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3273466","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5299999713897705},{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1528802670","https://openalex.org/W2096733369","https://openalex.org/W2101498401","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2340690086","https://openalex.org/W2467281799","https://openalex.org/W2471768434","https://openalex.org/W2605102252","https://openalex.org/W2747635822","https://openalex.org/W2774267535","https://openalex.org/W2798951647","https://openalex.org/W2883311563","https://openalex.org/W2883672875","https://openalex.org/W2885402090","https://openalex.org/W2900464008","https://openalex.org/W2905544595","https://openalex.org/W2953037339","https://openalex.org/W2962964995","https://openalex.org/W2963176022","https://openalex.org/W2963180826","https://openalex.org/W2963306451","https://openalex.org/W2963910742","https://openalex.org/W2964067226","https://openalex.org/W2964157791","https://openalex.org/W2964211610","https://openalex.org/W2966817867","https://openalex.org/W2980088508","https://openalex.org/W2985951359","https://openalex.org/W2994818707","https://openalex.org/W2998356391","https://openalex.org/W3014013608","https://openalex.org/W3025297341","https://openalex.org/W3026458074","https://openalex.org/W3034585290","https://openalex.org/W3034692043","https://openalex.org/W3035552787","https://openalex.org/W3038703236","https://openalex.org/W3119510203","https://openalex.org/W3154902219","https://openalex.org/W3159583533","https://openalex.org/W3172514680","https://openalex.org/W3175684172","https://openalex.org/W3176909828","https://openalex.org/W3203247393","https://openalex.org/W3205173298","https://openalex.org/W3206012133","https://openalex.org/W3206128852","https://openalex.org/W3206569427","https://openalex.org/W4205474609","https://openalex.org/W4206811189","https://openalex.org/W4288638391","https://openalex.org/W4312940158","https://openalex.org/W6730323794","https://openalex.org/W6739901393","https://openalex.org/W6747225742","https://openalex.org/W6751039726","https://openalex.org/W6757843237","https://openalex.org/W6766904570","https://openalex.org/W6768730002","https://openalex.org/W6776175912","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/W2384506582","https://openalex.org/W2034539438","https://openalex.org/W2130191173","https://openalex.org/W1787428848","https://openalex.org/W2188202313","https://openalex.org/W2735794310"],"abstract_inverted_index":{"Composed":[0],"image":[1,84,100,133,204,214,231,244],"retrieval":[2],"(CIR)":[3],"is":[4,71,91],"an":[5,162],"emerging":[6],"and":[7,18,50,120,139,156,185,234],"challenging":[8],"research":[9],"task":[10],"that":[11,256],"combines":[12],"two":[13,63,125,150],"modalities,":[14],"a":[15,19,222],"reference":[16,49],"image,":[17],"modification":[20,39,93,218,227,239],"text,":[21],"into":[22],"one":[23],"query":[24],"to":[25,43,56,67,76,96,129,192,202,224],"retrieve":[26],"the":[27,34,38,45,48,51,58,72,83,87,92,99,104,114,117,149,166,194,200,203,217,226,238,248,257,264],"target":[28],"image.":[29,53],"In":[30,54],"online":[31],"shopping":[32],"scenarios,":[33],"user":[35],"would":[36],"use":[37],"text":[40,201,209,242],"as":[41],"feedback":[42],"describe":[44],"difference":[46],"between":[47,123],"desired":[52],"order":[55],"handle":[57],"task,":[59,168],"there":[60],"must":[61],"be":[62,68,130,136],"main":[64],"problems":[65],"needed":[66],"addressed.":[69],"One":[70],"localization":[73,195],"problem:":[74,94],"how":[75,95],"precisely":[77,137,198],"find":[78],"those":[79],"spatial":[80,119,155],"areas":[81,205],"of":[82,229,241],"mentioned":[85],"by":[86,206],"text.":[88,105],"The":[89],"other":[90],"effectively":[97,236],"modify":[98],"semantics":[101],"based":[102,246],"on":[103,212,247,252],"However,":[106],"existing":[107],"methods":[108],"merely":[109],"fuse":[110],"information":[111,147,211],"coarsely":[112],"from":[113,148,154],"two-modality,":[115],"while":[116],"accurate":[118],"semantic":[121,157,232],"correspondence":[122],"these":[124],"heterogeneous":[126],"features":[127],"tends":[128],"neglected.":[131],"Therefore,":[132],"details":[134],"cannot":[135],"located":[138],"modified.":[140],"To":[141],"this":[142],"end,":[143],"we":[144,160],"consider":[145],"integrating":[146],"modalities":[151],"more":[152],"accurately":[153],"aspects.":[158],"Thus,":[159],"propose":[161],"end-to-end":[163],"framework":[164],"for":[165],"CIR":[167],"which":[169],"contains":[170],"three":[171,253],"key":[172],"components,":[173],"i.e.,":[174],"Multi-level":[175],"Collaborative":[176],"Localization":[177],"module":[178,183],"(MCL),":[179],"Differential":[180],"Semantics":[181],"Discrimination":[182],"(DSD),":[184],"Image":[186],"Difference":[187],"Enhancement":[188],"constraints":[189],"(IDE).":[190],"Specifically,":[191],"solve":[193],"problem,":[196,219],"MCL":[197],"locates":[199],"collaboratively":[207],"using":[208],"positioning":[210],"multiple":[213],"layers.":[215],"For":[216],"DSD":[220],"builds":[221],"distribution":[223],"evaluate":[225],"possibility":[228],"each":[230],"dimension,":[233],"IDE":[235],"learns":[237],"patterns":[240],"against":[243,263],"embedding":[245],"distribution.":[249],"Extensive":[250],"experiments":[251],"datasets":[254],"show":[255],"proposed":[258],"method":[259],"achieves":[260],"outstanding":[261],"performance":[262],"SOTA":[265],"methods.":[266]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}