{"id":"https://openalex.org/W4394744354","doi":"https://doi.org/10.1109/tip.2024.3385980","title":"ISTR: Mask-Embedding-Based Instance Segmentation Transformer","display_name":"ISTR: Mask-Embedding-Based Instance Segmentation Transformer","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4394744354","doi":"https://doi.org/10.1109/tip.2024.3385980","pmid":"https://pubmed.ncbi.nlm.nih.gov/38607701"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2024.3385980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3385980","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/A5100679572","display_name":"Jie Hu","orcid":"https://orcid.org/0000-0002-3187-1656"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Hu","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-3187-1656","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023665864","display_name":"Yao Lu","orcid":"https://orcid.org/0009-0006-7247-1153"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Lu","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0006-7247-1153","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012257365","display_name":"Shengchuan Zhang","orcid":"https://orcid.org/0000-0002-0824-4945"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengchuan Zhang","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014628588","display_name":"Liujuan Cao","orcid":"https://orcid.org/0000-0002-7645-9606"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liujuan Cao","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-7645-9606","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":2.7579,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.9169879,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"33","issue":null,"first_page":"2895","last_page":"2907"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9973000288009644,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9905999898910522,"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":0.7084690928459167},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6781327724456787},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6426447033882141},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5504150390625},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5278159379959106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5024211406707764},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49883055686950684},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.4404789209365845},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24771207571029663},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12225085496902466},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10774767398834229},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08669158816337585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7084690928459167},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6781327724456787},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6426447033882141},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5504150390625},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5278159379959106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5024211406707764},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49883055686950684},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.4404789209365845},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24771207571029663},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12225085496902466},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10774767398834229},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08669158816337585},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2024.3385980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3385980","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:38607701","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38607701","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/G1271955826","display_name":"\u57fa\u4e8e\u5f31\u76d1\u7763\u5b66\u4e60\u7684\u673a\u8f7d\u5730/\u6d77\u5c0f\u76ee\u6807\u68c0\u6d4b\u7814\u7a76","funder_award_id":"62072387","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1627692989","display_name":null,"funder_award_id":"2021J01002","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G1787173488","display_name":"\u9762\u5411\u6df1\u5ea6\u5b66\u4e60\u7684\u5bf9\u6297\u653b\u9632\u6280\u672f\u7814\u7a76","funder_award_id":"62072389","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2785666877","display_name":null,"funder_award_id":"62002305","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3568142893","display_name":null,"funder_award_id":"62272401","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4229650515","display_name":null,"funder_award_id":"2022ZD0118202","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5284885812","display_name":null,"funder_award_id":"62176222","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6075090814","display_name":null,"funder_award_id":"62025603","funder_id":"https://openalex.org/F4320336125","funder_display_name":"National Science Fund for Distinguished Young Scholars"},{"id":"https://openalex.org/G6727647225","display_name":null,"funder_award_id":"62176226","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G717600273","display_name":null,"funder_award_id":"U22B2051","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7220565969","display_name":null,"funder_award_id":"2022J06001","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G7272499820","display_name":null,"funder_award_id":"U21B2037","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7779606772","display_name":null,"funder_award_id":"62176223","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8406165135","display_name":"\u9762\u5411\u56fe\u654f\u611f\u6df1\u5ea6\u5b66\u4e60\u7684\u7ed3\u6784\u5316\u8d85\u56fe\u7814\u7a76","funder_award_id":"62072386","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"},{"id":"https://openalex.org/F4320321878","display_name":"Natural Science Foundation of Fujian Province","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2031614119","https://openalex.org/W2089468765","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2555182955","https://openalex.org/W2565639579","https://openalex.org/W2601564443","https://openalex.org/W2744404335","https://openalex.org/W2777795072","https://openalex.org/W2920326761","https://openalex.org/W2921781974","https://openalex.org/W2962766617","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2963849369","https://openalex.org/W2963857746","https://openalex.org/W2965182628","https://openalex.org/W2981537222","https://openalex.org/W2982161360","https://openalex.org/W2982770724","https://openalex.org/W2989676862","https://openalex.org/W2993182889","https://openalex.org/W3034421924","https://openalex.org/W3034428102","https://openalex.org/W3034681942","https://openalex.org/W3034826836","https://openalex.org/W3035049382","https://openalex.org/W3035709993","https://openalex.org/W3092462694","https://openalex.org/W3096609285","https://openalex.org/W3106546328","https://openalex.org/W3110109236","https://openalex.org/W3113410735","https://openalex.org/W3117450517","https://openalex.org/W3138516171","https://openalex.org/W3167260844","https://openalex.org/W3170019900","https://openalex.org/W3170841864","https://openalex.org/W3171162369","https://openalex.org/W3172752666","https://openalex.org/W3177165656","https://openalex.org/W4200050447","https://openalex.org/W4206706211","https://openalex.org/W4214613769","https://openalex.org/W4214654781","https://openalex.org/W4297426812","https://openalex.org/W4300479382","https://openalex.org/W4312263794","https://openalex.org/W4312815172","https://openalex.org/W4367595576","https://openalex.org/W4368755498","https://openalex.org/W4375868981","https://openalex.org/W4375928714","https://openalex.org/W4385245566","https://openalex.org/W4386071792","https://openalex.org/W4387074829","https://openalex.org/W6757817989","https://openalex.org/W6781390150","https://openalex.org/W6784094891","https://openalex.org/W6784930956","https://openalex.org/W6787290549","https://openalex.org/W6788071488","https://openalex.org/W6790749177","https://openalex.org/W6796402304","https://openalex.org/W6797784111","https://openalex.org/W6798837711","https://openalex.org/W6804552856","https://openalex.org/W6845518869","https://openalex.org/W6852669933","https://openalex.org/W6856710578"],"related_works":["https://openalex.org/W1916685473","https://openalex.org/W2055682261","https://openalex.org/W1993363272","https://openalex.org/W2186390138","https://openalex.org/W2060035984","https://openalex.org/W2790129917","https://openalex.org/W2992856432","https://openalex.org/W2100638064","https://openalex.org/W2127787376","https://openalex.org/W2212883587"],"abstract_inverted_index":{"Transformer-based":[0,26],"instance-level":[1],"recognition":[2],"has":[3,236],"attracted":[4],"increasing":[5],"research":[6],"attention":[7],"recently":[8],"due":[9],"to":[10,20,29,220],"the":[11,50,67,109,116,128,150,163,175,187,196,202,225],"superior":[12],"performance.":[13,177],"However,":[14],"although":[15],"attempts":[16],"have":[17],"been":[18,237],"made":[19,238],"encode":[21],"masks":[22],"as":[23,120,136],"embeddings":[24,32,194],"into":[25],"frameworks,":[27],"how":[28],"combine":[30],"mask":[31,81,112,117,193],"and":[33,55,76,102,141,165,171,184,189,215],"spatial":[34,78,164],"information":[35,75,79,123,167],"for":[36],"a":[37,85,92,97,103,121,147,152,212],"transformer-based":[38],"approach":[39],"is":[40,158],"still":[41],"not":[42],"fully":[43],"explored.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48],"revisit":[49],"design":[51],"of":[52,69,91,111,131,191],"mask-embedding-based":[53,209],"pipelines":[54],"propose":[56],"an":[57],"Instance":[58],"Segmentation":[59],"TRansformer":[60],"(ISTR)":[61],"with":[62,146,195],"Mask":[63,98,104,155],"Meta-Embeddings":[64],"(MME),":[65],"leveraging":[66],"strengths":[68],"transformer":[70],"models":[71,210],"in":[72],"encoding":[73],"embedding":[74,166],"incorporating":[77,192],"from":[80,169],"embeddings.":[82],"ISTR":[83,205,228],"incorporates":[84],"recurrent":[86],"refining":[87],"head":[88],"that":[89],"consists":[90],"Dynamic":[93],"Box":[94],"Predictor":[95],"(DBP),":[96],"Information":[99],"Generator":[100],"(MIG),":[101],"Meta-Decoder":[105],"(MMD).":[106],"To":[107],"improve":[108],"quality":[110],"embeddings,":[113],"MME":[114],"interprets":[115],"encoding-decoding":[118],"processes":[119],"mutual":[122],"maximization":[124],"problem,":[125],"which":[126,161],"unifies":[127],"objective":[129],"functions":[130],"different":[132],"decoding":[133],"schemes":[134],"such":[135],"Principal":[137],"Component":[138],"Analysis":[139],"(PCA)":[140],"Discrete":[142],"Cosine":[143],"Transform":[144],"(DCT)":[145],"meta-formulation.":[148],"Under":[149],"meta-formulation,":[151],"learnable":[153],"Spatial":[154],"Tuner":[156],"(SMT)":[157],"further":[159],"proposed,":[160],"fuses":[162],"produced":[168],"MIG":[170],"can":[172],"significantly":[173],"boost":[174],"segmentation":[176,199],"The":[178],"resulting":[179],"varieties,":[180],"i.e.,":[181],"ISTR-PCA,":[182],"ISTR-DCT,":[183],"ISTR-SMT,":[185],"demonstrate":[186],"effectiveness":[188],"efficiency":[190],"query-based":[197],"instance":[198],"pipelines.":[200],"On":[201,224],"COCO":[203],"dataset,":[204,227],"surpasses":[206],"all":[207],"predominant":[208],"by":[211],"large":[213],"margin,":[214],"achieves":[216],"competitive":[217],"performance":[218],"compared":[219],"concurrent":[221],"state-of-the-art":[222],"models.":[223],"Cityscapes":[226],"also":[229],"outperforms":[230],"several":[231],"strong":[232],"baselines.":[233],"Our":[234],"code":[235],"available":[239],"at:":[240],"https://github.com/hujiecpp/ISTR.":[241]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}