{"id":"https://openalex.org/W4415834960","doi":"https://doi.org/10.1142/s0218001425540217","title":"Unlocking the Potential of Auxiliary Captions via Dual-Branch Multi-Scale Network for Composed Image Retrieval","display_name":"Unlocking the Potential of Auxiliary Captions via Dual-Branch Multi-Scale Network for Composed Image Retrieval","publication_year":2025,"publication_date":"2025-11-04","ids":{"openalex":"https://openalex.org/W4415834960","doi":"https://doi.org/10.1142/s0218001425540217"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001425540217","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001425540217","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","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":null,"display_name":"Jinhong Xu","orcid":"https://orcid.org/0009-0001-9918-5783"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhong Xu","raw_affiliation_strings":["School of Computer, Electronics and Information, Guangxi University, Nanning 530004, China"],"raw_orcid":"https://orcid.org/0009-0001-9918-5783","affiliations":[{"raw_affiliation_string":"School of Computer, Electronics and Information, Guangxi University, Nanning 530004, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008154497","display_name":"Lina Yang","orcid":"https://orcid.org/0000-0003-3489-1887"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lina Yang","raw_affiliation_strings":["School of Computer, Electronics and Information, Guangxi University, Nanning 530004, China"],"raw_orcid":"https://orcid.org/0000-0003-3489-1887","affiliations":[{"raw_affiliation_string":"School of Computer, Electronics and Information, Guangxi University, Nanning 530004, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114626582","display_name":"Xichun Li","orcid":"https://orcid.org/0009-0006-1921-1651"},"institutions":[{"id":"https://openalex.org/I4210118063","display_name":"Guangxi Normal University for Nationalities","ror":"https://ror.org/02cejc171","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210118063"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xichun Li","raw_affiliation_strings":["School of Mathematics and Computer Science, Guangxi Normal University for Nationalities, Chongzuo 532200, China"],"raw_orcid":"https://orcid.org/0009-0006-1921-1651","affiliations":[{"raw_affiliation_string":"School of Mathematics and Computer Science, Guangxi Normal University for Nationalities, Chongzuo 532200, China","institution_ids":["https://openalex.org/I4210118063"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Thomas Wu","orcid":"https://orcid.org/0000-0002-0674-9915"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Thomas Wu","raw_affiliation_strings":["School of Electrical Engineering, Guangxi University, Nanning 530004, China"],"raw_orcid":"https://orcid.org/0000-0002-0674-9915","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, Nanning 530004, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085140523","display_name":"Yuan Yan Tang","orcid":"https://orcid.org/0000-0002-6887-130X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]},{"id":"https://openalex.org/I2800531931","display_name":"Hong Kong College of Technology","ror":"https://ror.org/014w0p014","country_code":"CN","type":"education","lineage":["https://openalex.org/I2800531931"]}],"countries":["CN","HK","MO"],"is_corresponding":false,"raw_author_name":"Yuan Yan Tang","raw_affiliation_strings":["Faculty of Science and Technology, UOW College Hong Kong, Hong Kong, China","Faculty of Science and Technology, University of Macau, Macau 999078, China"],"raw_orcid":"https://orcid.org/0000-0002-6887-130X","affiliations":[{"raw_affiliation_string":"Faculty of Science and Technology, UOW College Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I2800531931"]},{"raw_affiliation_string":"Faculty of Science and Technology, University of Macau, Macau 999078, China","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077075722","display_name":"Patrick S. P. Wang","orcid":"https://orcid.org/0000-0002-9336-3155"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Shen-Pei Wang","raw_affiliation_strings":["Department of Computer and Information Science, Khoury College of Computer Sciences, Northeastern University, MA 02115, Boston, USA"],"raw_orcid":"https://orcid.org/0000-0002-9336-3155","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, Khoury College of Computer Sciences, Northeastern University, MA 02115, Boston, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.251952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"02","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9472000002861023,"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":0.9472000002861023,"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":0.02199999988079071,"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":0.01860000006854534,"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/closed-captioning","display_name":"Closed captioning","score":0.718500018119812},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6908000111579895},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6496999859809875},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5896000266075134},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5734999775886536},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5371999740600586},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5307000279426575},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4065000116825104},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.39910000562667847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8259999752044678},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.718500018119812},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6908000111579895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6725000143051147},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6496999859809875},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5896000266075134},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5734999775886536},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5371999740600586},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5307000279426575},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4065000116825104},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.39910000562667847},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.38609999418258667},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.36800000071525574},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.3637999892234802},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C2986492983","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image matching","level":3,"score":0.32359999418258667},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31299999356269836},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.3077999949455261},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.2782999873161316},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.2750000059604645},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218001425540217","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001425540217","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3150721642","display_name":null,"funder_award_id":"62461004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7226221071","display_name":null,"funder_award_id":"62371144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7494446569","display_name":null,"funder_award_id":"62172458","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2250384498","https://openalex.org/W2255466643","https://openalex.org/W2905544595","https://openalex.org/W2962964995","https://openalex.org/W3026458074","https://openalex.org/W3049478012","https://openalex.org/W3090449556","https://openalex.org/W3154902219","https://openalex.org/W3155230099","https://openalex.org/W3169472988","https://openalex.org/W3172514680","https://openalex.org/W3175684172","https://openalex.org/W3203247393","https://openalex.org/W4224929299","https://openalex.org/W4230405732","https://openalex.org/W4280543555","https://openalex.org/W4285606530","https://openalex.org/W4292828970","https://openalex.org/W4295308727","https://openalex.org/W4296915201","https://openalex.org/W4304091775","https://openalex.org/W4312200802","https://openalex.org/W4313145975","https://openalex.org/W4313855701","https://openalex.org/W4372348803","https://openalex.org/W4375801927","https://openalex.org/W4385486155","https://openalex.org/W4386075952","https://openalex.org/W4386501573","https://openalex.org/W4390100115","https://openalex.org/W4390203954","https://openalex.org/W4390453039","https://openalex.org/W4392059258","https://openalex.org/W4392203450","https://openalex.org/W4393159792","https://openalex.org/W4394625619","https://openalex.org/W4395483878","https://openalex.org/W4405741836","https://openalex.org/W4407485672","https://openalex.org/W4409290618","https://openalex.org/W4409366480"],"related_works":[],"abstract_inverted_index":{"Composed":[0],"image":[1,13,64],"retrieval":[2],"(CIR)":[3],"aims":[4],"to":[5,28,76,108,135],"retrieve":[6],"target":[7],"images":[8],"by":[9,62],"combining":[10,48],"a":[11,15,40,47,51,85,95],"reference":[12],"with":[14,23],"modification":[16],"text.":[17],"Traditional":[18],"CIR":[19],"methods":[20],"often":[21],"struggle":[22],"feature-level":[24],"multimodal":[25,87],"fusion,":[26],"leading":[27],"deviations":[29],"from":[30],"the":[31,57,69,116],"original":[32],"embedding":[33],"space.":[34],"To":[35,55],"address":[36],"this,":[37],"we":[38],"propose":[39],"Dual-Branch":[41],"Multi-Scale":[42],"Network":[43],"(DMN)":[44],"that":[45,123],"integrates":[46],"branch":[49],"and":[50,83,102,119],"complete":[52],"text":[53],"branch.":[54],"enhance":[56,109],"use":[58],"of":[59,133],"captions":[60],"generated":[61],"advanced":[63],"captioning":[65],"models":[66],"for":[67,90],"CIR,":[68],"DMN":[70,125],"leverages":[71],"an":[72],"attribute-driven":[73],"disentanglement":[74],"layer":[75],"separate":[77],"features":[78],"into":[79],"distinct":[80],"latent":[81],"factors":[82],"employs":[84],"dual-path":[86],"fusion":[88],"module":[89,98],"effective":[91],"feature":[92,111],"integration.":[93],"Additionally,":[94],"multi-scale":[96],"matching":[97,104],"incorporating":[99],"both":[100],"global":[101],"local":[103],"strategies":[105],"is":[106],"introduced":[107],"fine-grained":[110],"discrimination.":[112],"Experimental":[113],"results":[114],"on":[115],"FashionIQ,":[117],"Shoes,":[118],"CIRR":[120],"datasets":[121],"demonstrate":[122],"our":[124],"model":[126],"consistently":[127],"outperforms":[128],"state-of-the-art":[129],"methods,":[130],"achieving":[131],"improvements":[132],"up":[134],"1.43%":[136],"in":[137],"mean":[138],"recall":[139],"metrics.":[140]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-11-04T00:00:00"}