{"id":"https://openalex.org/W7128534494","doi":"https://doi.org/10.1109/tcsvt.2026.3663260","title":"Revisiting Frequency Domain: Spatial-Frequency Joint Tuning for Referring Image Segmentation","display_name":"Revisiting Frequency Domain: Spatial-Frequency Joint Tuning for Referring Image Segmentation","publication_year":2026,"publication_date":"2026-02-10","ids":{"openalex":"https://openalex.org/W7128534494","doi":"https://doi.org/10.1109/tcsvt.2026.3663260"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3663260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3663260","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5125523392","display_name":"Guyue Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guyue Hu","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, and Anhui Provincial Key Laboratory of Security Artificial Intelligence, School of Artificial Intelligence, State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-6198-8230","affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, and Anhui Provincial Key Laboratory of Security Artificial Intelligence, School of Artificial Intelligence, State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046255961","display_name":"Yuxing Tong","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxing Tong","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, and Anhui Provincial Key Laboratory of Security Artificial Intelligence, School of Artificial Intelligence, State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Anhui University, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, and Anhui Provincial Key Laboratory of Security Artificial Intelligence, School of Artificial Intelligence, State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongtao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongtao Liu","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Intelligent Detection and Diagnosis for Traffic Infrastructure, Anhui Jiaojian Traffic Development and Research Center Company Ltd., Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Intelligent Detection and Diagnosis for Traffic Infrastructure, Anhui Jiaojian Traffic Development and Research Center Company Ltd., Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125495338","display_name":"Dong Geng","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Geng","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Intelligent Detection and Diagnosis for Traffic Infrastructure, Anhui Jiaojian Traffic Development and Research Center Company Ltd., Hefei, China"],"raw_orcid":"https://orcid.org/0009-0006-1356-4798","affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Intelligent Detection and Diagnosis for Traffic Infrastructure, Anhui Jiaojian Traffic Development and Research Center Company Ltd., Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chenglong Li","orcid":"https://orcid.org/0000-0002-7233-2739"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Li","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, and Anhui Provincial Key Laboratory of Security Artificial Intelligence, School of Artificial Intelligence, State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-7233-2739","affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, and Anhui Provincial Key Laboratory of Security Artificial Intelligence, School of Artificial Intelligence, State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13682617,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"6","first_page":"8930","last_page":"8940"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6833999752998352,"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":0.6833999752998352,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.12200000137090683,"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":0.020899999886751175,"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/segmentation","display_name":"Segmentation","score":0.652899980545044},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6150000095367432},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5669999718666077},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5076000094413757},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5041000247001648},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.46790000796318054},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.45170000195503235},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4487999975681305}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7745000123977661},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7616000175476074},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.652899980545044},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6514000296592712},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6150000095367432},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5669999718666077},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5076000094413757},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5041000247001648},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.46790000796318054},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.45170000195503235},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4311000108718872},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.41620001196861267},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C100921725","wikidata":"https://www.wikidata.org/wiki/Q1650811","display_name":"Spatial frequency","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2892000079154968},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C112353826","wikidata":"https://www.wikidata.org/wiki/Q127313","display_name":"Active contour model","level":4,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3663260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3663260","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.764958381652832,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1113574028","display_name":null,"funder_award_id":"62506003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2599639279","display_name":null,"funder_award_id":"U24A20342","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2900664570","display_name":null,"funder_award_id":"2408085QF201","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"},{"id":"https://openalex.org/G845944294","display_name":null,"funder_award_id":"62376004","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/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Referring":[0],"image":[1,75,176],"segmentation":[2,148,177],"aims":[3],"at":[4],"segmenting":[5],"the":[6,29,37,45,183,188],"target":[7],"object":[8,18,91,118,134],"referred":[9],"by":[10],"a":[11,65,110,139],"natural":[12],"language":[13],"expression,":[14],"which":[15,121,150],"requires":[16],"semantic-level":[17,90],"understanding":[19,92,119],"and":[20,40,47,63,93,185],"pixel-level":[21,95],"contour":[22,96,147,164],"segmentation.":[23,76,165],"Existing":[24],"methods":[25],"are":[26],"limited":[27],"to":[28,126],"spatial":[30,46,158],"domain,":[31],"thus":[32],"ignoring":[33],"potential":[34],"discriminability":[35],"from":[36],"frequency":[38,48,61],"domain":[39,62],"missing":[41],"mutual":[42],"boost":[43],"between":[44],"domains,":[49],"also":[50],"facing":[51],"heavy":[52,153],"high-frequency":[53,141,154],"degeneration":[54,155],"issues.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59,108,137],"revisit":[60],"propose":[64],"novel":[66],"lightweight":[67],"spatial-frequency":[68,104,111,124,129],"joint":[69,112],"tuning":[70,105],"(SFJT)":[71],"plugin":[72],"for":[73,152,174],"referring":[74,175],"We":[77],"decompose":[78],"4":[79,170,179],"mainstream":[80,171],"methodology":[81,172],"paradigms":[82,173],"into":[83],"two":[84],"general":[85],"stages":[86],"consisting":[87],"of":[88,169,187],"roughly":[89],"precisely":[94],"segmentation,":[97],"then":[98],"respectively":[99],"enhance":[100],"them":[101],"with":[102],"parameter-efficient":[103],"strategies.":[106],"Specifically,":[107],"develop":[109],"prompting":[113],"technique":[114],"(SFJ-Prompt)":[115],"during":[116,145],"early":[117],"stage,":[120,149],"mines":[122],"bidirectional":[123],"information":[125],"realize":[127],"mutually":[128],"boosting,":[130],"facilitating":[131,161],"more":[132,162],"comprehensive":[133],"understanding.":[135],"Besides,":[136],"introduce":[138],"LoRA-based":[140],"auxiliary":[142],"branch":[143],"(HF-LoRA)":[144],"latter":[146],"compensates":[151],"issues":[156],"in":[157],"neural":[159],"networks,":[160],"precise":[163],"Eventually,":[166],"extensive":[167],"experiments":[168],"on":[178],"large-scale":[180],"datasets":[181],"demonstrate":[182],"effectiveness":[184],"superiority":[186],"proposed":[189],"method.":[190]},"counts_by_year":[],"updated_date":"2026-06-06T06:22:57.294733","created_date":"2026-02-11T00:00:00"}