{"id":"https://openalex.org/W4401977074","doi":"https://doi.org/10.3390/s24165375","title":"Decoupled Cross-Modal Transformer for Referring Video Object Segmentation","display_name":"Decoupled Cross-Modal Transformer for Referring Video Object Segmentation","publication_year":2024,"publication_date":"2024-08-20","ids":{"openalex":"https://openalex.org/W4401977074","doi":"https://doi.org/10.3390/s24165375","pmid":"https://pubmed.ncbi.nlm.nih.gov/39205068"},"language":"en","primary_location":{"id":"doi:10.3390/s24165375","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24165375","pdf_url":"https://www.mdpi.com/1424-8220/24/16/5375/pdf?version=1724150906","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/24/16/5375/pdf?version=1724150906","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112107846","display_name":"Ao Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I37448385","display_name":"China People's Public Security University","ror":"https://ror.org/05twya590","country_code":"CN","type":"education","lineage":["https://openalex.org/I37448385"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ao Wu","raw_affiliation_strings":["School of Information and Cyber Security, People\u2019s Public Security University of China, Beijing 100038, China","School of Information and Cyber Security, People's Public Security University of China, Beijing 100038, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Cyber Security, People\u2019s Public Security University of China, Beijing 100038, China","institution_ids":["https://openalex.org/I37448385"]},{"raw_affiliation_string":"School of Information and Cyber Security, People's Public Security University of China, Beijing 100038, China","institution_ids":["https://openalex.org/I37448385"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030351224","display_name":"Rong Wang","orcid":"https://orcid.org/0000-0001-9240-6726"},"institutions":[{"id":"https://openalex.org/I1302611135","display_name":"Ministry of Public Security of the People's Republic of China","ror":"https://ror.org/00bt9we26","country_code":"CN","type":"government","lineage":["https://openalex.org/I1302611135"]},{"id":"https://openalex.org/I37448385","display_name":"China People's Public Security University","ror":"https://ror.org/05twya590","country_code":"CN","type":"education","lineage":["https://openalex.org/I37448385"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rong Wang","raw_affiliation_strings":["Key Laboratory of Security Prevention Technology and Risk Assessment of Ministry of Public Security, Beijing 100038, China","School of Information and Cyber Security, People\u2019s Public Security University of China, Beijing 100038, China","School of Information and Cyber Security, People's Public Security University of China, Beijing 100038, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Security Prevention Technology and Risk Assessment of Ministry of Public Security, Beijing 100038, China","institution_ids":["https://openalex.org/I1302611135"]},{"raw_affiliation_string":"School of Information and Cyber Security, People\u2019s Public Security University of China, Beijing 100038, China","institution_ids":["https://openalex.org/I37448385"]},{"raw_affiliation_string":"School of Information and Cyber Security, People's Public Security University of China, Beijing 100038, China","institution_ids":["https://openalex.org/I37448385"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050916960","display_name":"Quange Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I37448385","display_name":"China People's Public Security University","ror":"https://ror.org/05twya590","country_code":"CN","type":"education","lineage":["https://openalex.org/I37448385"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quange Tan","raw_affiliation_strings":["School of Information and Cyber Security, People\u2019s Public Security University of China, Beijing 100038, China","School of Information and Cyber Security, People's Public Security University of China, Beijing 100038, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Cyber Security, People\u2019s Public Security University of China, Beijing 100038, China","institution_ids":["https://openalex.org/I37448385"]},{"raw_affiliation_string":"School of Information and Cyber Security, People's Public Security University of China, Beijing 100038, China","institution_ids":["https://openalex.org/I37448385"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075295532","display_name":"Zhenfeng Song","orcid":"https://orcid.org/0000-0002-7652-4893"},"institutions":[{"id":"https://openalex.org/I37448385","display_name":"China People's Public Security University","ror":"https://ror.org/05twya590","country_code":"CN","type":"education","lineage":["https://openalex.org/I37448385"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenfeng Song","raw_affiliation_strings":["School of Information and Cyber Security, People\u2019s Public Security University of China, Beijing 100038, China","School of Information and Cyber Security, People's Public Security University of China, Beijing 100038, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Cyber Security, People\u2019s Public Security University of China, Beijing 100038, China","institution_ids":["https://openalex.org/I37448385"]},{"raw_affiliation_string":"School of Information and Cyber Security, People's Public Security University of China, Beijing 100038, China","institution_ids":["https://openalex.org/I37448385"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5030351224"],"corresponding_institution_ids":["https://openalex.org/I1302611135","https://openalex.org/I37448385"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2673},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2673},"fwci":0.4935,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60426217,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"24","issue":"16","first_page":"5375","last_page":"5375"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9987000226974487,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9962000250816345,"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":0.7991938591003418},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6365713477134705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5954537391662598},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5665289163589478},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5516015291213989},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4582199156284332},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4177058935165405},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32919859886169434}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7991938591003418},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6365713477134705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5954537391662598},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5665289163589478},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5516015291213989},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4582199156284332},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4177058935165405},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32919859886169434},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3390/s24165375","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24165375","pdf_url":"https://www.mdpi.com/1424-8220/24/16/5375/pdf?version=1724150906","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:39205068","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39205068","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11359580","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11359580","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11359580/pdf/sensors-24-05375.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:9e36b5651e1e4bde895508fe7cb1dfdb","is_oa":true,"landing_page_url":"https://doaj.org/article/9e36b5651e1e4bde895508fe7cb1dfdb","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 24, Iss 16, p 5375 (2024)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/24/16/5375/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s24165375","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s24165375","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24165375","pdf_url":"https://www.mdpi.com/1424-8220/24/16/5375/pdf?version=1724150906","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6899999976158142,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G2441086882","display_name":null,"funder_award_id":"2023SYL08","funder_id":"https://openalex.org/F4320330924","funder_display_name":"People's Public Security University of China"}],"funders":[{"id":"https://openalex.org/F4320330924","display_name":"People's Public Security University of China","ror":"https://ror.org/05twya590"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401977074.pdf","grobid_xml":"https://content.openalex.org/works/W4401977074.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W2034014085","https://openalex.org/W2222512263","https://openalex.org/W2302548814","https://openalex.org/W2565639579","https://openalex.org/W2605127024","https://openalex.org/W2769833683","https://openalex.org/W2889986507","https://openalex.org/W2962914239","https://openalex.org/W2963253279","https://openalex.org/W2963351448","https://openalex.org/W2963354481","https://openalex.org/W2964345792","https://openalex.org/W2980088508","https://openalex.org/W2983693499","https://openalex.org/W2997063389","https://openalex.org/W3008914387","https://openalex.org/W3034692043","https://openalex.org/W3094664776","https://openalex.org/W3096609285","https://openalex.org/W3104844437","https://openalex.org/W3108432914","https://openalex.org/W3108748824","https://openalex.org/W3122784054","https://openalex.org/W3135367836","https://openalex.org/W3138516171","https://openalex.org/W3153471465","https://openalex.org/W3159619744","https://openalex.org/W3171516518","https://openalex.org/W3178075329","https://openalex.org/W3201770677","https://openalex.org/W3215899623","https://openalex.org/W4200631575","https://openalex.org/W4226024706","https://openalex.org/W4292779060","https://openalex.org/W4312560592","https://openalex.org/W4312690830","https://openalex.org/W4390872515","https://openalex.org/W6778883912","https://openalex.org/W6788885258","https://openalex.org/W6798505901"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2404514746","https://openalex.org/W1652783584","https://openalex.org/W2082783427","https://openalex.org/W4386159726"],"abstract_inverted_index":{"Referring":[0],"video":[1,22,94],"object":[2,95,144],"segmentation":[3,203],"(R-VOS)":[4],"is":[5,173],"a":[6,108,136,141],"fundamental":[7],"vision-language":[8],"task":[9],"which":[10],"aims":[11],"to":[12,44,52,97,114,119,146,175],"segment":[13],"the":[14,33,46,49,53,62,71,158,167,207],"target":[15],"referred":[16],"by":[17,162,180],"language":[18],"expression":[19],"in":[20,70,78],"all":[21,123],"frames.":[23],"Existing":[24],"query-based":[25],"R-VOS":[26],"methods":[27],"have":[28,187],"conducted":[29],"in-depth":[30],"exploration":[31],"of":[32,48,61,73,122,129,143],"interaction":[34],"and":[35,39,101,153,194],"alignment":[36],"between":[37],"visual":[38,120,152,178],"linguistic":[40,117,154],"features":[41,121,155],"but":[42],"fail":[43],"transfer":[45],"information":[47,68,118,149],"two":[50],"modalities":[51],"query":[54],"vector":[55],"with":[56,206],"balanced":[57],"intensities.":[58],"Furthermore,":[59],"most":[60],"traditional":[63],"approaches":[64],"suffer":[65],"from":[66,150],"severe":[67],"loss":[69],"process":[72],"multi-scale":[74,102],"feature":[75,163],"fusion,":[76],"resulting":[77],"inaccurate":[79],"segmentation.":[80],"In":[81],"this":[82],"paper,":[83],"we":[84,105,134],"propose":[85,135],"DCT,":[86],"an":[87,126],"end-to-end":[88],"decoupled":[89,137],"cross-modal":[90],"transformer":[91,138],"for":[92],"referring":[93],"segmentation,":[96],"better":[98],"utilize":[99],"multi-modal":[100],"information.":[103],"Specifically,":[104],"first":[106],"design":[107],"Language-Guided":[109],"Visual":[110],"Enhancement":[111],"Module":[112],"(LGVE)":[113],"transmit":[115],"discriminative":[116],"levels,":[124],"performing":[125],"initial":[127],"filtering":[128],"irrelevant":[130],"background":[131],"regions.":[132],"Then,":[133],"decoder,":[139],"using":[140],"set":[142],"queries":[145],"gather":[147],"entity-related":[148],"both":[151],"independently,":[156],"mitigating":[157],"attention":[159],"bias":[160],"caused":[161],"size":[164],"differences.":[165],"Finally,":[166],"Cross-layer":[168],"Feature":[169],"Pyramid":[170],"Network":[171],"(CFPN)":[172],"introduced":[174],"preserve":[176],"more":[177],"details":[179],"establishing":[181],"direct":[182],"cross-layer":[183],"communication.":[184],"Extensive":[185],"experiments":[186],"been":[188],"carried":[189],"out":[190],"on":[191],"A2D-Sentences,":[192],"JHMDB-Sentences":[193],"Ref-Youtube-VOS.":[195],"The":[196],"results":[197],"show":[198],"that":[199],"DCT":[200],"achieves":[201],"competitive":[202],"accuracy":[204],"compared":[205],"state-of-the-art":[208],"methods.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}