{"id":"https://openalex.org/W4416873244","doi":"https://doi.org/10.1109/tgrs.2025.3639131","title":"GRRSIS: Generalized Referring Remote Sensing Image Segmentation","display_name":"GRRSIS: Generalized Referring Remote Sensing Image Segmentation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416873244","doi":"https://doi.org/10.1109/tgrs.2025.3639131"},"language":null,"primary_location":{"id":"doi:10.1109/tgrs.2025.3639131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3639131","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"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 Geoscience and Remote Sensing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5022144594","display_name":"Wenyu Mi","orcid":"https://orcid.org/0000-0002-4777-5327"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenyu Mi","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, and the Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi’an Jiaotong University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, and the Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","institution_ids":[]},{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101587109","display_name":"Jianji Wang","orcid":"https://orcid.org/0000-0002-4284-3933"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianji Wang","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, and the Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi’an Jiaotong University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, and the Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","institution_ids":[]},{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041921496","display_name":"Fuzhen Zhuang","orcid":"https://orcid.org/0000-0001-9170-7009"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuzhen Zhuang","raw_affiliation_strings":["Institute of Artificial Intelligence, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047405956","display_name":"Nanning Zheng","orcid":"https://orcid.org/0000-0003-1608-8257"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nanning Zheng","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, and the Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi’an Jiaotong University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, and the Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China","institution_ids":[]},{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5022144594"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3784341,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"63","issue":null,"first_page":"1","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.3691999912261963,"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":0.3691999912261963,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1454000025987625,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.14339999854564667,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/segmentation","display_name":"Segmentation","score":0.664900004863739},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5781999826431274},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5479999780654907},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.49779999256134033},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4934999942779541},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4894999861717224},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4772999882698059},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.4648999869823456},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4603999853134155},{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.4431999921798706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8360999822616577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7210000157356262},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.664900004863739},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5992000102996826},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5781999826431274},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5479999780654907},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.49779999256134033},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4934999942779541},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4894999861717224},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4772999882698059},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.4648999869823456},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4603999853134155},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.4431999921798706},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.44269999861717224},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4327000081539154},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3619999885559082},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.3540000021457672},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.320499986410141},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C32653426","wikidata":"https://www.wikidata.org/wiki/Q3813641","display_name":"Background subtraction","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.28940001130104065},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.2685999870300293},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2678999900817871},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26510000228881836},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2565999925136566},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2025.3639131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3639131","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"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 Geoscience and Remote Sensing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3833898155","display_name":null,"funder_award_id":"62088102","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W2064675550","https://openalex.org/W2108598243","https://openalex.org/W2131774270","https://openalex.org/W2136848157","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2302548814","https://openalex.org/W2605127024","https://openalex.org/W2770888309","https://openalex.org/W2798556392","https://openalex.org/W2896457183","https://openalex.org/W2980088508","https://openalex.org/W2991363140","https://openalex.org/W3034692043","https://openalex.org/W3035428952","https://openalex.org/W3081684346","https://openalex.org/W3108748824","https://openalex.org/W3138516171","https://openalex.org/W3178075329","https://openalex.org/W3187664142","https://openalex.org/W3201770677","https://openalex.org/W3216551675","https://openalex.org/W4200631575","https://openalex.org/W4292258945","https://openalex.org/W4304084012","https://openalex.org/W4312543911","https://openalex.org/W4376851337","https://openalex.org/W4385245566","https://openalex.org/W4385764483","https://openalex.org/W4386065815","https://openalex.org/W4386075493","https://openalex.org/W4386076142","https://openalex.org/W4389371459","https://openalex.org/W4390874500","https://openalex.org/W4392397297","https://openalex.org/W4404202521","https://openalex.org/W4404612934","https://openalex.org/W4404628512","https://openalex.org/W4404840231","https://openalex.org/W4409985823"],"related_works":[],"abstract_inverted_index":{"Referring":[0,91],"Remote":[1,92],"Sensing":[2,93,174],"Image":[3,94],"Segmentation":[4,95],"(RRSIS)":[5],"is":[6,41],"a":[7,16,21,61,66,71,86,144,182,201],"challenging":[8],"task":[9],"that":[10,136,176],"involves":[11],"segmenting":[12],"target":[13,31,36],"instances":[14],"within":[15],"top-view":[17],"image":[18],"guided":[19],"by":[20,38,101,224,233],"natural":[22],"language":[23],"expression.":[24],"Existing":[25],"classic":[26,99,254],"RRSIS":[27,100,255],"methods":[28],"commonly":[29],"support":[30],"expressions":[32,47,103],"only,":[33],"i.e.,":[34],"the":[35,39,44,53,75,113,134,221,230,249],"described":[37],"expression":[40],"present":[42,154],"in":[43,81,130,138],"image.":[45],"No-target":[46],"are":[48],"excluded.":[49],"Under":[50],"this":[51,79,82],"constraint,":[52],"model":[54],"may":[55],"face":[56],"significant":[57,150],"challenges.":[58],"For":[59],"instance,":[60],"small":[62,145],"error,":[63],"such":[64],"as":[65],"typographical":[67],"mistake,":[68],"could":[69],"cause":[70],"complete":[72],"failure":[73],"of":[74,147,157,212],"model.":[76],"To":[77,160],"overcome":[78],"issue,":[80],"paper,":[83],"we":[84,111,164,199],"introduce":[85,200],"new":[87],"benchmark":[88],"called":[89,119],"Generalized":[90],"(GRRSIS),":[96],"which":[97,121,208],"extends":[98],"allowing":[102],"to":[104,106,185,214],"refer":[105],"no-target":[107,126],"objects.":[108],"Towards":[109],"this,":[110],"construct":[112],"first":[114],"large-scale":[115],"dataset":[116],"for":[117,194],"GRRSIS,":[118],"GRRSIS-D,":[120],"includes":[122],"multi-target,":[123],"single-target,":[124],"and":[125,153,181,216,219,237,253],"expressions.":[127],"Core":[128],"challenges":[129],"GRRSIS":[131,252],"stem":[132],"from":[133],"fact":[135],"objects":[137],"aerial":[139],"images":[140],"often":[141],"occupy":[142],"only":[143],"number":[146],"pixels,":[148],"exhibit":[149],"orientation":[151],"variations,":[152],"varying":[155,210],"levels":[156,211],"recognition":[158],"difficulty.":[159,240],"tackle":[161],"these":[162],"challenges,":[163],"propose":[165],"an":[166,171],"Oriented-aware":[167],"Multi-Scale":[168],"Network":[169],"with":[170],"Adaptive":[172,178],"Angle":[173],"module":[175],"integrates":[177],"Rotated":[179],"Convolution":[180],"gating":[183],"mechanism":[184],"capture":[186],"diverse":[187],"object":[188],"orientations":[189],"while":[190],"suppressing":[191],"irrelevant":[192],"features":[193],"more":[195],"accurate":[196],"representations.":[197],"Additionally,":[198],"novel":[202],"Online":[203],"Hard":[204],"Case":[205],"Mining":[206],"Loss,":[207],"allocates":[209],"attention":[213],"foreground":[215],"background":[217],"regions":[218],"reshapes":[220],"standard":[222],"loss":[223],"down-weighting":[225],"well-segmented":[226],"examples,":[227],"effectively":[228],"addressing":[229],"issues":[231],"caused":[232],"low":[234],"pixel":[235],"occupancy":[236],"uneven":[238],"sample":[239],"The":[241],"proposed":[242],"approach":[243],"achieves":[244],"state-of-the-art":[245],"performance":[246],"on":[247],"both":[248],"newly":[250],"introduced":[251],"tasks.":[256]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-12-01T00:00:00"}