{"id":"https://openalex.org/W7151250827","doi":"https://doi.org/10.1109/tcsvt.2026.3681596","title":"MiCA: Intra-Modal Integration and Cross-Modal Alignment Adapters for Parameter-Efficient Referring Image Segmentation","display_name":"MiCA: Intra-Modal Integration and Cross-Modal Alignment Adapters for Parameter-Efficient Referring Image Segmentation","publication_year":2026,"publication_date":"2026-04-07","ids":{"openalex":"https://openalex.org/W7151250827","doi":"https://doi.org/10.1109/tcsvt.2026.3681596"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3681596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3681596","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/A5133120387","display_name":"Yang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":"https://orcid.org/0000-0001-5672-4110","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133136655","display_name":"Zitong Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zitong Feng","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":"https://orcid.org/0009-0003-7599-445X","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133082687","display_name":"Tingrui Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingrui Wang","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032609144","display_name":"Chenyu Wang","orcid":"https://orcid.org/0009-0007-6443-0260"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyu Wang","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":"https://orcid.org/0009-0007-0510-3307","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101644680","display_name":"Xin Zhou","orcid":"https://orcid.org/0000-0002-1496-405X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Zhou","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":"https://orcid.org/0000-0002-1496-405X","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30544781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"8","first_page":"12465","last_page":"12478"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.23409999907016754,"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":0.23409999907016754,"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":0.16249999403953552,"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":0.10450000315904617,"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/image-segmentation","display_name":"Image segmentation","score":0.6212999820709229},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4627000093460083},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.4165000021457672},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.4142000079154968},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3921999931335449},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38190001249313354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.737500011920929},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6897000074386597},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6657999753952026},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.6212999820709229},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4627000093460083},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.4165000021457672},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.4142000079154968},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3921999931335449},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.3021000027656555},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.28200000524520874},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26930001378059387},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2565999925136566},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3681596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3681596","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W2251512949","https://openalex.org/W2302548814","https://openalex.org/W2489434015","https://openalex.org/W2605127024","https://openalex.org/W2798556392","https://openalex.org/W2919842726","https://openalex.org/W2979727876","https://openalex.org/W3138516171","https://openalex.org/W3159619744","https://openalex.org/W3198377975","https://openalex.org/W3216551675","https://openalex.org/W4200631575","https://openalex.org/W4312310776","https://openalex.org/W4312543911","https://openalex.org/W4312651322","https://openalex.org/W4312884055","https://openalex.org/W4313054169","https://openalex.org/W4386065815","https://openalex.org/W4386071547","https://openalex.org/W4386075493","https://openalex.org/W4386076034","https://openalex.org/W4386076142","https://openalex.org/W4386083036","https://openalex.org/W4386790226","https://openalex.org/W4390871886","https://openalex.org/W4390873429","https://openalex.org/W4390873528","https://openalex.org/W4390874575","https://openalex.org/W4395064954","https://openalex.org/W4401043311","https://openalex.org/W4402703023","https://openalex.org/W4402703104","https://openalex.org/W4402727789","https://openalex.org/W4402754134","https://openalex.org/W4402979572","https://openalex.org/W4403488721","https://openalex.org/W4403791725","https://openalex.org/W4403998622","https://openalex.org/W4404011646","https://openalex.org/W4404783315","https://openalex.org/W4404840231","https://openalex.org/W4405974258","https://openalex.org/W4408564121","https://openalex.org/W4409128969","https://openalex.org/W4409368383","https://openalex.org/W4413146904","https://openalex.org/W4415444078","https://openalex.org/W4415796235","https://openalex.org/W4416037134","https://openalex.org/W7133202389","https://openalex.org/W7133219196"],"related_works":[],"abstract_inverted_index":{"Parameter-efficient":[0],"transfer":[1],"learning":[2],"(PETL)":[3],"has":[4],"emerged":[5],"as":[6,39],"an":[7],"effective":[8],"strategy":[9],"for":[10],"fine-tuning":[11,144],"large":[12],"vision\u2013language":[13],"foundation":[14],"models":[15],"because":[16],"it":[17],"sharply":[18],"reduces":[19],"computational":[20],"and":[21,55,68,116,118,145],"memory":[22],"overhead.":[23],"However,":[24],"existing":[25],"PETL":[26,63,147],"techniques":[27],"underperform":[28],"on":[29,123],"dense":[30],"prediction":[31],"tasks":[32],"that":[33,50,129],"require":[34],"fine-grained":[35],"multimodal":[36,120],"reasoning,":[37],"such":[38],"referring":[40],"image":[41],"segmentation":[42],"(RIS),":[43],"owing":[44],"to":[45,141,167],"the":[46,111,132,142,163,168],"lack":[47],"of":[48],"mechanisms":[49],"simultaneously":[51],"strengthen":[52],"local":[53,90],"perception":[54],"enforce":[56],"precise":[57],"cross-modal":[58],"alignment.":[59],"We":[60],"present":[61],"a":[62,85],"framework":[64],"with":[65,84,105,150],"two":[66],"lightweight":[67,86],"complementary":[69],"adapters.":[70],"The":[71,96],"Global\u2013Local":[72],"Integrated":[73],"Adapter":[74,99],"(GLiA)":[75],"enriches":[76],"intra-modal":[77],"features":[78],"by":[79,160],"coupling":[80],"multi-scale":[81],"depthwise-separable":[82],"convolutions":[83],"self-attention":[87],"layer,":[88],"capturing":[89],"context":[91],"without":[92],"sacrificing":[93],"global":[94],"dependencies.":[95],"Cross-Modal":[97],"Alignment":[98],"(CAA)":[100],"explicitly":[101],"aligns":[102],"textual":[103],"phrases":[104],"their":[106],"corresponding":[107],"visual":[108],"regions,":[109],"bridging":[110],"semantic":[112],"gap":[113],"between":[114],"vision":[115],"language":[117],"enhancing":[119],"reasoning.":[121],"Experiments":[122],"three":[124,164],"mainstream":[125],"RIS":[126],"benchmarks":[127,165],"show":[128],"MiCA":[130,156],"achieves":[131],"best":[133],"accuracy":[134,159],"while":[135],"saving":[136],"numerous":[137],"updated":[138],"parameters":[139],"compared":[140,166],"full":[143],"other":[146],"methods.":[148],"Notably,":[149],"only":[151],"1.93%":[152],"tunable":[153],"backbone":[154],"parameters,":[155],"improves":[157],"average":[158],"0.8%":[161],"across":[162],"baseline":[169],"model.":[170]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-04-08T00:00:00"}