{"id":"https://openalex.org/W4415055544","doi":"https://doi.org/10.1109/tpami.2026.3683307","title":"Text4Seg++: Advancing Image Segmentation via Generative Language Modeling","display_name":"Text4Seg++: Advancing Image Segmentation via Generative Language Modeling","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W4415055544","doi":"https://doi.org/10.1109/tpami.2026.3683307","pmid":"https://pubmed.ncbi.nlm.nih.gov/41973591"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3683307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3683307","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","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.06321","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009052131","display_name":"Mengcheng Lan","orcid":"https://orcid.org/0000-0002-3311-0295"},"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":"Mengcheng Lan","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-3311-0295","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chaofeng Chen","orcid":"https://orcid.org/0000-0001-6137-5162"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaofeng Chen","raw_affiliation_strings":["School of Artificial Intelligence, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-6137-5162","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027071312","display_name":"Jiaxing Xu","orcid":"https://orcid.org/0000-0003-0845-2645"},"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":"Jiaxing Xu","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-2498-5812","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101943794","display_name":"Zongrui Li","orcid":"https://orcid.org/0009-0003-4357-9593"},"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":"Zongrui Li","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0009-0003-4357-9593","affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074491217","display_name":"Yiping Ke","orcid":"https://orcid.org/0000-0001-9473-3202"},"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":"Yiping Ke","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-9473-3202","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","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, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-9104-2315","affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090126397","display_name":"Yingchen Yu","orcid":"https://orcid.org/0000-0002-7893-0764"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingchen Yu","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7893-0764","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060204146","display_name":"Yunqing Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunqing Zhao","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2661-3169","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101562162","display_name":"Song Bai","orcid":"https://orcid.org/0000-0002-2570-9118"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song Bai","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2570-9118","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01210934,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"8","first_page":"9486","last_page":"9501"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9437000155448914,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9437000155448914,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9279000163078308,"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/segmentation","display_name":"Segmentation","score":0.7972000241279602},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.5741999745368958},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5636000037193298},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.5625},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5453000068664551},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5128999948501587},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4578999876976013},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42260000109672546},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4156999886035919},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.41040000319480896}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7972000241279602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7915999889373779},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6593000292778015},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.5741999745368958},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5636000037193298},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.5625},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5453000068664551},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5128999948501587},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4578999876976013},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4090999960899353},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4023999869823456},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3774999976158142},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.36880001425743103},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3474000096321106},{"id":"https://openalex.org/C77660490","wikidata":"https://www.wikidata.org/wiki/Q244916","display_name":"Intermediate language","level":3,"score":0.34630000591278076},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.32899999618530273},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.28940001130104065},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.2865000069141388},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2540999948978424},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tpami.2026.3683307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3683307","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:41973591","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41973591","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:2509.06321","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.06321","pdf_url":"https://arxiv.org/pdf/2509.06321","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},{"id":"doi:10.48550/arxiv.2509.06321","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.06321","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.06321","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.06321","pdf_url":"https://arxiv.org/pdf/2509.06321","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"have":[5],"shown":[6],"exceptional":[7],"capabilities":[8],"in":[9],"vision-language":[10],"tasks.":[11,144],"However,":[12],"effectively":[13],"integrating":[14],"image":[15,34,68,234],"segmentation":[16,35,51,64,88,136,184,235],"into":[17,93],"these":[18],"models":[19,209],"remains":[20],"a":[21,28,37,59,83,139,186],"significant":[22],"challenge.In":[23],"this":[24],"work,":[25],"we":[26,101,151],"propose":[27,152],"novel":[29],"text-as-mask":[30],"paradigm":[31],"that":[32,90,205],"casts":[33],"as":[36,185],"text":[38,75,111],"generation":[39],"problem,":[40],"eliminating":[41],"the":[42,50,94,103,114,227,237],"need":[43],"for":[44],"additional":[45],"decoders":[46],"and":[47,120,149,164,193,200,230],"significantly":[48],"simplifying":[49],"process.":[52],"Our":[53,224],"key":[54],"innovation":[55],"is":[56,70],"semantic":[57,81,117,154,173],"descriptors,":[58,82,155],"new":[60],"textual":[61,85],"representation":[62,86],"of":[63,87,116,142,159,232],"masks":[65,89,167],"where":[66],"each":[67],"patch":[69],"mapped":[71],"to":[72,177],"its":[73],"corresponding":[74],"label.":[76],"We":[77],"first":[78],"introduce":[79,102],"image-wise":[80],"patch-aligned":[84],"integrates":[91],"naturally":[92],"language":[95],"modeling":[96],"pipeline.":[97],"To":[98,145],"enhance":[99],"efficiency,":[100],"Row-wise":[104],"Run-Length":[105],"Encoding":[106],"(R-RLE),":[107],"which":[108,156,182],"compresses":[109],"redundant":[110],"sequences,":[112],"reducing":[113],"length":[115],"descriptorsby":[118],"74%":[119],"accelerating":[121],"inference":[122],"by":[123],"$3\\times$3\u00d7,":[124],"without":[125,213],"compromising":[126],"performance.":[127],"Building":[128],"upon":[129],"this,":[130],"our":[131,178],"initial":[132],"framework":[133],"Text4Segachieves":[134],"strong":[135],"performance":[137],"across":[138,210],"wide":[140],"range":[141],"vision":[143],"further":[146],"improve":[147],"granularity":[148],"compactness,":[150],"box-wise":[153],"localizes":[157],"regions":[158],"interest":[160],"using":[161],"bounding":[162],"boxes":[163],"represents":[165],"region":[166],"via":[168],"structured":[169],"mask":[170],"tokens":[171],"called":[172],"bricks.":[174],"This":[175],"leads":[176],"refined":[179],"model,":[180],"Text4Seg++,":[181],"formulates":[183],"next-brick":[187],"prediction":[188],"task,":[189],"combining":[190],"precision,":[191],"scalability,":[192,229],"generative":[194],"efficiency.":[195],"Comprehensive":[196],"experiments":[197],"on":[198],"natural":[199],"remote":[201],"sensing":[202],"datasets":[203],"show":[204],"Text4Seg++consistently":[206],"outperforms":[207],"state-of-the-art":[208],"diverse":[211],"benchmarks":[212],"any":[214],"task-specific":[215],"fine-tuning,":[216],"while":[217],"remaining":[218],"compatible":[219],"with":[220],"existing":[221],"MLLM":[222,238],"backbones.":[223],"work":[225],"highlights":[226],"effectiveness,":[228],"generalizability":[231],"text-driven":[233],"within":[236],"framework.":[239]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-11T00:00:00"}