{"id":"https://openalex.org/W4404294163","doi":"https://doi.org/10.1109/tip.2024.3492713","title":"PVPUFormer: Probabilistic Visual Prompt Unified Transformer for Interactive Image Segmentation","display_name":"PVPUFormer: Probabilistic Visual Prompt Unified Transformer for Interactive Image Segmentation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404294163","doi":"https://doi.org/10.1109/tip.2024.3492713","pmid":"https://pubmed.ncbi.nlm.nih.gov/39531563"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2024.3492713","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3492713","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Image Processing","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/A5100437310","display_name":"Xu Zhang","orcid":"https://orcid.org/0000-0003-3632-4464"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xu Zhang","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027010844","display_name":"Kailun Yang","orcid":"https://orcid.org/0000-0002-1090-667X"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kailun Yang","raw_affiliation_strings":["School of Robotics, National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Robotics, National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101566662","display_name":"Jiacheng Lin","orcid":"https://orcid.org/0000-0003-1393-5027"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiacheng Lin","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100603557","display_name":"Jin Yuan","orcid":"https://orcid.org/0000-0002-9600-7789"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Yuan","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396723","display_name":"Zhiyong Li","orcid":"https://orcid.org/0000-0001-9720-5915"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Li","raw_affiliation_strings":["College of Computer Science and Electronic Engineering and the School of Robotics, National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering and the School of Robotics, National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067097659","display_name":"Shutao Li","orcid":"https://orcid.org/0000-0002-0585-9848"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shutao Li","raw_affiliation_strings":["School of Robotics, National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Robotics, National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100437310"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":0.7291,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72918447,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"33","issue":null,"first_page":"6455","last_page":"6468"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9455999732017517,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9455999732017517,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9355000257492065,"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":0.9243000149726868,"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":0.68919837474823},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6861035227775574},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.6637742519378662},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6356824040412903},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5946999788284302},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5101283192634583},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.5083710551261902},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.4399111270904541},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.32166969776153564}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.68919837474823},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6861035227775574},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.6637742519378662},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6356824040412903},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5946999788284302},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5101283192634583},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.5083710551261902},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.4399111270904541},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.32166969776153564}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2024.3492713","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3492713","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Image Processing","raw_type":"journal-article"},{"id":"pmid:39531563","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39531563","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 image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1548865700","display_name":null,"funder_award_id":"62473139","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4041047505","display_name":null,"funder_award_id":"U23A20341","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8354495100","display_name":null,"funder_award_id":"U21A20518","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8637866159","display_name":null,"funder_award_id":"62272157","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":69,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1995714461","https://openalex.org/W1995911388","https://openalex.org/W2003192903","https://openalex.org/W2121927366","https://openalex.org/W2124351162","https://openalex.org/W2125637308","https://openalex.org/W2144794286","https://openalex.org/W2169551590","https://openalex.org/W2194775991","https://openalex.org/W2300469113","https://openalex.org/W2470139095","https://openalex.org/W2533218643","https://openalex.org/W2565639579","https://openalex.org/W2737258237","https://openalex.org/W2787091153","https://openalex.org/W2803537647","https://openalex.org/W2890143105","https://openalex.org/W2940262938","https://openalex.org/W2948553897","https://openalex.org/W2948672349","https://openalex.org/W2962914239","https://openalex.org/W2962967409","https://openalex.org/W2964307987","https://openalex.org/W3010908644","https://openalex.org/W3034278117","https://openalex.org/W3034550159","https://openalex.org/W3034586976","https://openalex.org/W3093597327","https://openalex.org/W3108925098","https://openalex.org/W3115654959","https://openalex.org/W3121058064","https://openalex.org/W3132926949","https://openalex.org/W3175701034","https://openalex.org/W4214588164","https://openalex.org/W4225773438","https://openalex.org/W4225787400","https://openalex.org/W4281756654","https://openalex.org/W4287100534","https://openalex.org/W4308235913","https://openalex.org/W4312336332","https://openalex.org/W4312371888","https://openalex.org/W4312517459","https://openalex.org/W4312603257","https://openalex.org/W4318141851","https://openalex.org/W4353007612","https://openalex.org/W4385245566","https://openalex.org/W4386065433","https://openalex.org/W4386075720","https://openalex.org/W4386075998","https://openalex.org/W4386076245","https://openalex.org/W4387968027","https://openalex.org/W4390872677","https://openalex.org/W4390872789","https://openalex.org/W4390873051","https://openalex.org/W4390874575","https://openalex.org/W4393149930","https://openalex.org/W4393159149","https://openalex.org/W4393285773","https://openalex.org/W4394560274","https://openalex.org/W6761630670","https://openalex.org/W6774415586","https://openalex.org/W6783683508","https://openalex.org/W6797399245","https://openalex.org/W6798128096","https://openalex.org/W6838936497","https://openalex.org/W6850592984","https://openalex.org/W6851607685","https://openalex.org/W6864221053"],"related_works":["https://openalex.org/W1986655823","https://openalex.org/W2185902295","https://openalex.org/W2103507220","https://openalex.org/W3144569342","https://openalex.org/W3011384228","https://openalex.org/W2124969951","https://openalex.org/W2945274617","https://openalex.org/W4313052709","https://openalex.org/W4298131179","https://openalex.org/W2375430703"],"abstract_inverted_index":{"Integration":[0],"of":[1,34,196],"diverse":[2,82],"visual":[3,83],"prompts":[4,35,84],"like":[5],"clicks,":[6],"scribbles,":[7],"and":[8,90,96,122,150,184],"boxes":[9],"in":[10,44],"interactive":[11,73,212],"image":[12,74,183],"segmentation":[13,213],"significantly":[14],"facilitates":[15],"users'":[16],"interaction":[17,22,181],"as":[18,20],"well":[19],"improves":[21],"efficiency.":[23],"However,":[24],"existing":[25],"studies":[26],"primarily":[27],"encode":[28],"the":[29,38,86,154,204],"position":[30],"or":[31],"pixel":[32,151],"regions":[33],"without":[36],"considering":[37],"contextual":[39,124],"areas":[40],"around":[41],"them,":[42],"resulting":[43],"insufficient":[45],"prompt":[46,88,98,121,149,185],"feedback,":[47],"which":[48,76],"is":[49,217],"not":[50],"conducive":[51],"to":[52,79,93,112,130,145,159,177],"performance":[53,101,132,191],"acceleration.":[54],"To":[55],"tackle":[56],"this":[57,59,135],"problem,":[58],"paper":[60],"proposes":[61],"a":[62,107,114,140,171],"simple":[63],"yet":[64],"effective":[65],"Probabilistic":[66,108],"Visual":[67],"Prompt":[68],"Unified":[69],"Transformer":[70],"(PVPUFormer)":[71],"for":[72,100,164,190],"segmentation,":[75],"allows":[77],"users":[78],"flexibly":[80],"input":[81],"with":[85],"probabilistic":[87],"encoding":[89],"feature":[91,162,180],"post-processing":[92],"excavate":[94],"sufficient":[95],"robust":[97],"features":[99,189],"boosting.":[102],"Specifically,":[103],"we":[104,137],"first":[105],"propose":[106],"Prompt-unified":[109],"Encoder":[110],"(PPuE)":[111],"generate":[113],"unified":[115],"one-dimensional":[116],"vector":[117],"by":[118],"exploring":[119],"both":[120,148],"non-prompt":[123],"information,":[125],"offering":[126],"richer":[127],"feedback":[128],"cues":[129],"accelerate":[131],"improvement.":[133,192],"On":[134],"basis,":[136],"further":[138],"present":[139],"Prompt-to-Pixel":[141],"Contrastive":[142],"(P2C)":[143],"loss":[144],"accurately":[146],"align":[147],"features,":[152,186],"bridging":[153],"representation":[155],"gap":[156],"between":[157,182],"them":[158],"offer":[160],"consistent":[161,208],"representations":[163],"mask":[165],"prediction.":[166],"Moreover,":[167],"our":[168],"approach":[169],"designs":[170],"Dual-cross":[172],"Merging":[173],"Attention":[174],"(DMA)":[175],"module":[176],"implement":[178],"bidirectional":[179],"generating":[187],"notable":[188],"A":[193],"comprehensive":[194],"variety":[195],"experiments":[197],"on":[198],"several":[199],"challenging":[200],"datasets":[201],"demonstrates":[202],"that":[203],"proposed":[205],"components":[206],"achieve":[207],"improvements,":[209],"yielding":[210],"state-of-the-art":[211],"performance.":[214],"Our":[215],"code":[216],"available":[218],"at":[219],"https://github.com/XuZhang1211/PVPUFormer.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}