{"id":"https://openalex.org/W4312773871","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892139","title":"Region-based Cross-modal Retrieval","display_name":"Region-based Cross-modal Retrieval","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312773871","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892139"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892139","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5017840950","display_name":"Danyang Hou","orcid":"https://orcid.org/0009-0006-6949-2703"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Danyang Hou","raw_affiliation_strings":["Data Intelligence System Research Center, Institute of Computing Technology, CAS,Beijing,China","University of Chinese Academy of Sciences, Beijing, China","Data Intelligence System Research Center, Institute of Computing Technology, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Data Intelligence System Research Center, Institute of Computing Technology, CAS,Beijing,China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Data Intelligence System Research Center, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004759804","display_name":"Liang Pang","orcid":"https://orcid.org/0000-0003-1161-8546"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Pang","raw_affiliation_strings":["Data Intelligence System Research Center, Institute of Computing Technology, CAS,Beijing,China","Data Intelligence System Research Center, Institute of Computing Technology, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Data Intelligence System Research Center, Institute of Computing Technology, CAS,Beijing,China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Data Intelligence System Research Center, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101616866","display_name":"Yanyan Lan","orcid":"https://orcid.org/0000-0002-7811-3262"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyan Lan","raw_affiliation_strings":["Institute for AI Industry Research, Tsinghua University,Beijing,China","Institute for AI Industry Research, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research, Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Institute for AI Industry Research, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047897879","display_name":"Huawei Shen","orcid":"https://orcid.org/0000-0002-1081-8119"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huawei Shen","raw_affiliation_strings":["Data Intelligence System Research Center, Institute of Computing Technology, CAS,Beijing,China","Data Intelligence System Research Center, Institute of Computing Technology, CAS, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Data Intelligence System Research Center, Institute of Computing Technology, CAS,Beijing,China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Data Intelligence System Research Center, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029998682","display_name":"Xueqi Cheng","orcid":"https://orcid.org/0000-0002-5201-8195"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqi Cheng","raw_affiliation_strings":["Institute of Computing Technology, CAS,CAS Key Lab of Network Data Science and Technology,Beijing,China","CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology, CAS, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, CAS,CAS Key Lab of Network Data Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5017840950"],"corresponding_institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.06,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.321617,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9994999766349792,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9919999837875366,"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":0.8446121215820312},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5940132141113281},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5805496573448181},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5523232221603394},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5214935541152954},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5199607610702515},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5196067690849304},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.47531062364578247},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.46657073497772217},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.4588966369628906},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4555559754371643},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4489462077617645},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4241366386413574},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41722139716148376},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.36800748109817505},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10023680329322815}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8446121215820312},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5940132141113281},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5805496573448181},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5523232221603394},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5214935541152954},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5199607610702515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5196067690849304},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.47531062364578247},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.46657073497772217},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.4588966369628906},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4555559754371643},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4489462077617645},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4241366386413574},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41722139716148376},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36800748109817505},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10023680329322815},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892139","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6499999761581421,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5539197300","display_name":null,"funder_award_id":"61906180,U21B2046","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":47,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W2064675550","https://openalex.org/W2122762031","https://openalex.org/W2133564696","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2745461083","https://openalex.org/W2765440071","https://openalex.org/W2774267535","https://openalex.org/W2778940641","https://openalex.org/W2883311563","https://openalex.org/W2896457183","https://openalex.org/W2962964995","https://openalex.org/W2963109634","https://openalex.org/W2963758027","https://openalex.org/W2964120214","https://openalex.org/W2966715458","https://openalex.org/W2970231061","https://openalex.org/W2994818707","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3043547428","https://openalex.org/W3090449556","https://openalex.org/W3093067848","https://openalex.org/W3095670406","https://openalex.org/W3108984808","https://openalex.org/W3150772620","https://openalex.org/W3156636935","https://openalex.org/W3168433561","https://openalex.org/W4252076394","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6639102338","https://openalex.org/W6679434410","https://openalex.org/W6684191040","https://openalex.org/W6687483927","https://openalex.org/W6739901393","https://openalex.org/W6747225742","https://openalex.org/W6747457746","https://openalex.org/W6749537441","https://openalex.org/W6755207826","https://openalex.org/W6766904570","https://openalex.org/W6776721752","https://openalex.org/W6780931037"],"related_works":["https://openalex.org/W2063218608","https://openalex.org/W4386105885","https://openalex.org/W2071180033","https://openalex.org/W2184288218","https://openalex.org/W2947282851","https://openalex.org/W2374066281","https://openalex.org/W4387423606","https://openalex.org/W2147874738","https://openalex.org/W2036058638","https://openalex.org/W2513891871"],"abstract_inverted_index":{"Cross-modal":[0],"retrieval":[1,29,57],"aims":[2],"to":[3,87,123],"identify":[4],"relevant":[5],"information":[6],"from":[7],"different":[8],"modalities,":[9],"such":[10,43],"as":[11,44,110],"image":[12,23,115],"and":[13,24,38,46,71,77,116,120,138,142],"text.":[14,26],"Existing":[15],"works":[16],"build":[17],"a":[18,54,99],"coarse":[19],"relationship":[20],"between":[21,66],"whole":[22,25],"However,":[27],"the":[28,63,125,143,148,152],"in":[30,36,75,79],"fine-grained":[31,67,89],"elements":[32],"is":[33,86],"more":[34],"necessary":[35],"research":[37],"has":[39],"many":[40],"practical":[41],"applications,":[42],"explainable":[45],"interactive":[47],"retrieval.":[48],"In":[49],"this":[50,84,95],"paper,":[51],"we":[52,97],"propose":[53,98],"region-based":[55],"cross-modal":[56],"task":[58,85],"that":[59,147],"focuses":[60],"on":[61,135],"finding":[62],"semantic":[64],"match":[65],"parts":[68],"of":[69,83,129],"text":[70],"image,":[72],"e.g.,":[73],"sentence":[74],"paragraph":[76],"region":[78],"image.":[80],"The":[81],"challenge":[82],"enhance":[88],"representation":[90],"with":[91],"contextual":[92,126],"knowledge.":[93],"To":[94],"end,":[96],"Context-Aware":[100],"Region":[101],"Retrieval":[102],"(CARR)":[103],"model.":[104],"It":[105],"utilizes":[106],"two":[107,130],"pre-trained":[108],"models":[109],"backbones,":[111],"Faster":[112],"RCNN":[113],"for":[114,118],"BERT":[117],"text,":[119],"transformer-based":[121],"encoders":[122],"obtain":[124],"aware":[127],"representations":[128],"modalities.":[131],"We":[132],"conduct":[133],"experiments":[134],"Visual":[136],"Genome":[137],"Localized":[139],"Narratives":[140],"datasets,":[141],"experimental":[144],"results":[145],"demonstrate":[146],"proposed":[149],"model":[150],"outperforms":[151],"baseline":[153],"methods.":[154]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}