{"id":"https://openalex.org/W4307504011","doi":"https://doi.org/10.1109/tpami.2022.3217852","title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","display_name":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","publication_year":2022,"publication_date":"2022-11-04","ids":{"openalex":"https://openalex.org/W4307504011","doi":"https://doi.org/10.1109/tpami.2022.3217852","pmid":"https://pubmed.ncbi.nlm.nih.gov/36306296"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2022.3217852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3217852","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":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.15871","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036631624","display_name":"Henghui Ding","orcid":"https://orcid.org/0000-0003-4868-6526"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Henghui Ding","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University (NTU), Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353160","display_name":"Chang Liu","orcid":"https://orcid.org/0000-0001-6980-7791"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chang Liu","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University (NTU), Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020106541","display_name":"Suchen Wang","orcid":"https://orcid.org/0000-0002-4086-0713"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Suchen Wang","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University (NTU), Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085533260","display_name":"Xudong Jiang","orcid":"https://orcid.org/0000-0002-9104-2315"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xudong Jiang","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University (NTU), Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036631624"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":12.8696,"has_fulltext":false,"cited_by_count":133,"citation_normalized_percentile":{"value":0.99294552,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"45","issue":"6","first_page":"7900","last_page":"7916"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8529242873191833},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6911175847053528},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6007043123245239},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5701247453689575},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47702428698539734},{"id":"https://openalex.org/keywords/randomness","display_name":"Randomness","score":0.47124892473220825},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.413726270198822}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8529242873191833},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6911175847053528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6007043123245239},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5701247453689575},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47702428698539734},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.47124892473220825},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.413726270198822},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2022.3217852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3217852","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:36306296","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36306296","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:arXiv.org:2210.15871","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.15871","pdf_url":"https://arxiv.org/pdf/2210.15871","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2210.15871","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.15871","pdf_url":"https://arxiv.org/pdf/2210.15871","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":105,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W1924770834","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2302548814","https://openalex.org/W2412782625","https://openalex.org/W2489434015","https://openalex.org/W2558535589","https://openalex.org/W2605127024","https://openalex.org/W2605229288","https://openalex.org/W2770129969","https://openalex.org/W2798556392","https://openalex.org/W2842511635","https://openalex.org/W2876852810","https://openalex.org/W2894964039","https://openalex.org/W2896457183","https://openalex.org/W2904910963","https://openalex.org/W2916743882","https://openalex.org/W2936652946","https://openalex.org/W2946086442","https://openalex.org/W2962764817","https://openalex.org/W2962942822","https://openalex.org/W2963037989","https://openalex.org/W2963091558","https://openalex.org/W2963109634","https://openalex.org/W2963150697","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W2966715458","https://openalex.org/W2980088508","https://openalex.org/W2981413347","https://openalex.org/W2984121207","https://openalex.org/W2986803748","https://openalex.org/W2987734933","https://openalex.org/W3004019157","https://openalex.org/W3014611590","https://openalex.org/W3014641072","https://openalex.org/W3016719260","https://openalex.org/W3020827971","https://openalex.org/W3034325957","https://openalex.org/W3034692043","https://openalex.org/W3034772468","https://openalex.org/W3035097537","https://openalex.org/W3093025045","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3104844437","https://openalex.org/W3108748824","https://openalex.org/W3108925098","https://openalex.org/W3110435696","https://openalex.org/W3126792443","https://openalex.org/W3129576130","https://openalex.org/W3138516171","https://openalex.org/W3143320354","https://openalex.org/W3153666347","https://openalex.org/W3159619744","https://openalex.org/W3166396011","https://openalex.org/W3168640669","https://openalex.org/W3169998662","https://openalex.org/W3170841864","https://openalex.org/W3171098737","https://openalex.org/W3172522282","https://openalex.org/W3173220247","https://openalex.org/W3173859428","https://openalex.org/W3178075329","https://openalex.org/W3187664142","https://openalex.org/W3201770677","https://openalex.org/W3202427362","https://openalex.org/W3202576436","https://openalex.org/W3211490618","https://openalex.org/W3213165621","https://openalex.org/W3214642103","https://openalex.org/W3215863079","https://openalex.org/W3216551675","https://openalex.org/W4200631575","https://openalex.org/W4214490042","https://openalex.org/W4226024706","https://openalex.org/W4289126595","https://openalex.org/W4297808394","https://openalex.org/W4312543911","https://openalex.org/W4312560592","https://openalex.org/W4312940158","https://openalex.org/W4385245566","https://openalex.org/W6640212811","https://openalex.org/W6697921835","https://openalex.org/W6739901393","https://openalex.org/W6749526849","https://openalex.org/W6755207826","https://openalex.org/W6757135208","https://openalex.org/W6761380950","https://openalex.org/W6766904570","https://openalex.org/W6768730002","https://openalex.org/W6775188310","https://openalex.org/W6778485988","https://openalex.org/W6784333009","https://openalex.org/W6789753369","https://openalex.org/W6790978476","https://openalex.org/W6791353385","https://openalex.org/W6794092134","https://openalex.org/W6796280812","https://openalex.org/W6797399245","https://openalex.org/W6798505901","https://openalex.org/W6798837711","https://openalex.org/W6803039797","https://openalex.org/W6804418671"],"related_works":["https://openalex.org/W3049463507","https://openalex.org/W2936497627","https://openalex.org/W4288365749","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W4287598411","https://openalex.org/W3098382480","https://openalex.org/W3198458223","https://openalex.org/W4288267738","https://openalex.org/W3126642501"],"abstract_inverted_index":{"We":[0,159],"propose":[1,74,111],"a":[2,35,75,107,112],"Vision-Language":[3],"Transformer":[4],"(VLT)":[5],"framework":[6],"for":[7,172],"referring":[8,193],"segmentation":[9,194],"to":[10,22,29,87,105,116,128,143,155,164],"facilitate":[11],"deep":[12],"interactions":[13],"among":[14,99],"multi-modal":[15],"information":[16],"and":[17,62,189],"enhance":[18,129],"the":[19,31,42,45,60,66,89,97,119,123,130,146,156,167,173,179],"holistic":[20],"understanding":[21,151],"vision-language":[23],"features.":[24],"There":[25],"are":[26,52],"different":[27,152,170,182],"ways":[28],"understand":[30],"dynamic":[32],"emphasis":[33],"of":[34,65,84,92,122,125,150,169,181],"language":[36,67,93,137,153],"expression,":[37],"especially":[38],"when":[39],"interacting":[40],"with":[41,59,135,148],"image.":[43],"However,":[44],"learned":[46],"queries":[47,86],"in":[48,133],"existing":[49],"transformer":[50],"works":[51],"fixed":[53],"after":[54],"training,":[55],"which":[56,79],"cannot":[57],"cope":[58],"randomness":[61],"huge":[63],"diversity":[64],"expressions.":[68],"To":[69,95],"address":[70],"this":[71],"issue,":[72],"we":[73,110,139],"Query":[76,113],"Generation":[77],"Module,":[78],"dynamically":[80],"produces":[81],"multiple":[82],"sets":[83],"input-specific":[85],"represent":[88],"diverse":[90,101,136],"comprehensions":[91],"expression.":[94],"find":[96],"best":[98],"these":[100],"comprehensions,":[102],"so":[103],"as":[104],"generate":[106],"better":[108],"mask,":[109],"Balance":[114],"Module":[115],"selectively":[117],"fuse":[118],"corresponding":[120],"responses":[121],"set":[124],"queries.":[126],"Furthermore,":[127],"model's":[131],"ability":[132],"dealing":[134],"expressions,":[138],"consider":[140],"inter-sample":[141],"learning":[142,163],"explicitly":[144],"endow":[145],"model":[147],"knowledge":[149],"expressions":[154,171],"same":[157,174],"object.":[158],"introduce":[160],"masked":[161],"contrastive":[162],"narrow":[165],"down":[166],"features":[168,180],"target":[175],"object":[176],"while":[177],"distinguishing":[178],"objects.":[183],"The":[184],"proposed":[185],"approach":[186],"is":[187],"lightweight":[188],"achieves":[190],"new":[191],"state-of-the-art":[192],"results":[195],"consistently":[196],"on":[197],"five":[198],"datasets.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":54},{"year":2024,"cited_by_count":42},{"year":2023,"cited_by_count":29},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}