{"id":"https://openalex.org/W4402832800","doi":"https://doi.org/10.1109/tpami.2024.3468640","title":"Language-Aware Vision Transformer for Referring Segmentation","display_name":"Language-Aware Vision Transformer for Referring Segmentation","publication_year":2024,"publication_date":"2024-09-25","ids":{"openalex":"https://openalex.org/W4402832800","doi":"https://doi.org/10.1109/tpami.2024.3468640","pmid":"https://pubmed.ncbi.nlm.nih.gov/39321010"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3468640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3468640","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5102788842","display_name":"Zhao Yang","orcid":"https://orcid.org/0000-0003-4376-0109"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Zhao Yang","raw_affiliation_strings":["Shanghai AI Lab, Shanghai, China","Department of Engineering Science, University of Oxford, UK"],"raw_orcid":"https://orcid.org/0000-0003-4376-0109","affiliations":[{"raw_affiliation_string":"Shanghai AI Lab, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Department of Engineering Science, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365340","display_name":"Jiaqi Wang","orcid":"https://orcid.org/0000-0001-6877-5353"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Wang","raw_affiliation_strings":["Shanghai AI Lab, Shanghai, China","Shanghai AI Lab, China"],"raw_orcid":"https://orcid.org/0000-0001-6877-5353","affiliations":[{"raw_affiliation_string":"Shanghai AI Lab, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai AI Lab, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006963206","display_name":"Xubing Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Xubing Ye","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","Shenzhen International Graduate School, Tsinghua University, China"],"raw_orcid":"https://orcid.org/0009-0006-8269-2689","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101926293","display_name":"Yansong Tang","orcid":"https://orcid.org/0000-0002-1534-4549"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Yansong Tang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","Shenzhen International Graduate School, Tsinghua University, China"],"raw_orcid":"https://orcid.org/0000-0002-1534-4549","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077376788","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0002-6820-2325"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["Shanghai AI Lab, Shanghai, China","Shanghai AI Lab, China"],"raw_orcid":"https://orcid.org/0000-0002-6820-2325","affiliations":[{"raw_affiliation_string":"Shanghai AI Lab, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai AI Lab, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078109015","display_name":"Hengshuang Zhao","orcid":"https://orcid.org/0000-0001-8277-2706"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hengshuang Zhao","raw_affiliation_strings":["Department of Computer Science, University of Hong Kong, Pok Fu Lam, Hong Kong","Department of Computer Science, The University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-8277-2706","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Hong Kong, Pok Fu Lam, Hong Kong","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042899882","display_name":"Philip H. S. Torr","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip H. S. Torr","raw_affiliation_strings":["Department of Engineering Science, University of Oxford, Oxford, U.K","Department of Engineering Science, University of Oxford, UK"],"raw_orcid":"https://orcid.org/0009-0006-0259-5732","affiliations":[{"raw_affiliation_string":"Department of Engineering Science, University of Oxford, Oxford, U.K","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Department of Engineering Science, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102788842"],"corresponding_institution_ids":["https://openalex.org/I40120149","https://openalex.org/I4391012619"],"apc_list":null,"apc_paid":null,"fwci":2.3808,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.90147705,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"47","issue":"7","first_page":"5238","last_page":"5255"},"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":0.9524000287055969,"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":0.9524000287055969,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9441999793052673,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.683564305305481},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6575008630752563},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5788460373878479},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5579250454902649},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.537786066532135},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4493836760520935},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4460325837135315},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.419197678565979},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34863170981407166},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14237600564956665}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.683564305305481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6575008630752563},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5788460373878479},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5579250454902649},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.537786066532135},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4493836760520935},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4460325837135315},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.419197678565979},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34863170981407166},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14237600564956665},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2024.3468640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3468640","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:39321010","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39321010","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":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:ora.ox.ac.uk:uuid:3b9da0a1-9ba9-41f3-98ee-d1e6fa3ce3dc","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symplectic Elements","raw_type":"Journal article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G2438210826","display_name":null,"funder_award_id":"62321005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4599997883","display_name":null,"funder_award_id":"62201484","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6806237773","display_name":null,"funder_award_id":"62206153","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":93,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1861492603","https://openalex.org/W1903029394","https://openalex.org/W1905722737","https://openalex.org/W2034014085","https://openalex.org/W2064675550","https://openalex.org/W2065749455","https://openalex.org/W2108598243","https://openalex.org/W2138621090","https://openalex.org/W2302548814","https://openalex.org/W2489434015","https://openalex.org/W2507296351","https://openalex.org/W2565639579","https://openalex.org/W2605127024","https://openalex.org/W2798556392","https://openalex.org/W2876852810","https://openalex.org/W2894964039","https://openalex.org/W2896457183","https://openalex.org/W2945152522","https://openalex.org/W2962914239","https://openalex.org/W2962942822","https://openalex.org/W2963109634","https://openalex.org/W2963354481","https://openalex.org/W2963524571","https://openalex.org/W2963820951","https://openalex.org/W2964110616","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W2979826702","https://openalex.org/W2980088508","https://openalex.org/W2982723417","https://openalex.org/W2983693499","https://openalex.org/W2990205821","https://openalex.org/W2997063389","https://openalex.org/W3004019157","https://openalex.org/W3034325957","https://openalex.org/W3034692043","https://openalex.org/W3034804856","https://openalex.org/W3035097537","https://openalex.org/W3035524453","https://openalex.org/W3093025045","https://openalex.org/W3094664776","https://openalex.org/W3096609285","https://openalex.org/W3104844437","https://openalex.org/W3108748824","https://openalex.org/W3122784054","https://openalex.org/W3138516171","https://openalex.org/W3143320354","https://openalex.org/W3159619744","https://openalex.org/W3168640669","https://openalex.org/W3169998662","https://openalex.org/W3170841864","https://openalex.org/W3172522282","https://openalex.org/W3177892185","https://openalex.org/W3178075329","https://openalex.org/W3187664142","https://openalex.org/W3201770677","https://openalex.org/W3215899623","https://openalex.org/W4200631575","https://openalex.org/W4214612132","https://openalex.org/W4214893857","https://openalex.org/W4226024706","https://openalex.org/W4226058394","https://openalex.org/W4288052482","https://openalex.org/W4307504011","https://openalex.org/W4312560592","https://openalex.org/W4312690830","https://openalex.org/W4312933868","https://openalex.org/W4379984073","https://openalex.org/W4382240193","https://openalex.org/W4385245566","https://openalex.org/W4386065815","https://openalex.org/W4386075493","https://openalex.org/W4386076034","https://openalex.org/W4386076142","https://openalex.org/W4390873204","https://openalex.org/W4390873614","https://openalex.org/W4390874496","https://openalex.org/W6724804524","https://openalex.org/W6730323794","https://openalex.org/W6739696289","https://openalex.org/W6750227808","https://openalex.org/W6757817989","https://openalex.org/W6759534164","https://openalex.org/W6763701032","https://openalex.org/W6766904570","https://openalex.org/W6766978945","https://openalex.org/W6784094891","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6791353385","https://openalex.org/W6881022228","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W2501551404","https://openalex.org/W4385583601","https://openalex.org/W4298131179","https://openalex.org/W2113201962","https://openalex.org/W4395685956","https://openalex.org/W2799953226","https://openalex.org/W4398146871","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Referring":[0],"segmentation":[1,189,275,280,294],"is":[2,34,63,208,305],"a":[3,22,66,77,81,111,140,162,178,195,209,231,244,262],"fundamental":[4],"vision-language":[5,68,108],"task":[6,33],"that":[7,119,265],"aims":[8],"to":[9,64,71,100,301],"segment":[10],"out":[11],"an":[12,15],"object":[13],"from":[14,76],"image":[16,45,58,269,293],"or":[17,46],"video":[18,47,61,221,226,271,297],"in":[19,43,55,90,105,114,136,154,204,243],"accordance":[20],"with":[21,194,220,273],"natural":[23],"language":[24,82],"description.":[25],"One":[26,199],"of":[27,131,139,149,177,200,234],"the":[28,36,44,57,60,101,128,147,155,172,201,205,225],"key":[29,202],"challenges":[30],"behind":[31],"this":[32,53,91,115,235],"leveraging":[35],"referring":[37,279,292,296],"expression":[38],"for":[39,51,181,213,291],"highlighting":[40],"relevant":[41],"positions":[42],"frames.":[48],"A":[49],"paradigm":[50,92],"tackling":[52],"problem":[54],"both":[56,268],"and":[59,80,133,229,270,295],"domains":[62],"leverage":[65],"powerful":[67],"(\"cross-modal\")":[69],"decoder":[70],"fuse":[72],"features":[73,135],"independently":[74],"extracted":[75],"vision":[78,141],"encoder":[79,143,180],"encoder.":[83],"Recent":[84],"methods":[85,283,287],"have":[86],"made":[87],"remarkable":[88],"advances":[89],"by":[93,237],"exploiting":[94],"Transformers":[95],"as":[96,261],"cross-modal":[97,122,151],"decoders,":[98],"concurrent":[99],"Transformer's":[102],"overwhelming":[103],"success":[104],"many":[106],"other":[107],"tasks.":[109],"Adopting":[110],"different":[112,253],"approach":[113],"work,":[116],"we":[117,160,223],"show":[118],"significantly":[120],"better":[121],"alignments":[123],"can":[124,191,248],"be":[125,192],"achieved":[126],"through":[127],"early":[129],"fusion":[130,153],"linguistic":[132,216],"visual":[134,156],"intermediate":[137],"layers":[138],"Transformer":[142,168,179],"network.":[144],"Based":[145],"on":[146,277,288],"idea":[148],"conducting":[150],"feature":[152,157],"encoding":[158],"stage,":[159],"propose":[161],"unified":[163,259,263,278],"framework":[164,228,264],"named":[165],"Language-Aware":[166],"Vision":[167],"(LAVT),":[169],"which":[170,247],"leverages":[171],"well-proven":[173],"correlation":[174],"modeling":[175],"power":[176],"excavating":[182],"helpful":[183],"multi-modal":[184],"context.":[185],"This":[186],"way,":[187],"accurate":[188],"results":[190],"harvested":[193],"light-weight":[196],"mask":[197],"predictor.":[198],"components":[203],"proposed":[206],"system":[207],"dense":[210],"attention":[211],"mechanism":[212],"collecting":[214],"pixel-specific":[215],"cues.":[217],"When":[218],"dealing":[219],"inputs,":[222],"present":[224],"LAVT":[227,260],"design":[230],"3D":[232],"version":[233],"component":[236],"introducing":[238],"multi-scale":[239],"convolutional":[240],"operators":[241],"arranged":[242],"parallel":[245],"fashion,":[246],"exploit":[249],"spatio-temporal":[250],"dependencies":[251],"at":[252,307],"granularity":[254],"levels.":[255],"We":[256],"further":[257],"introduce":[258],"could":[266],"handle":[267],"inputs":[272],"enhanced":[274],"capability":[276],"task.":[281],"Our":[282],"surpass":[284],"previous":[285],"state-of-the-art":[286],"seven":[289],"benchmarks":[290],"segmentation.":[298],"The":[299],"code":[300],"reproduce":[302],"our":[303],"experiments":[304],"available":[306],"LAVT-RS.":[308]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":6}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}