{"id":"https://openalex.org/W4377711491","doi":"https://doi.org/10.1109/tip.2023.3277791","title":"Multi-Modal Mutual Attention and Iterative Interaction for Referring Image Segmentation","display_name":"Multi-Modal Mutual Attention and Iterative Interaction for Referring Image Segmentation","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4377711491","doi":"https://doi.org/10.1109/tip.2023.3277791","pmid":"https://pubmed.ncbi.nlm.nih.gov/37220044"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2023.3277791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3277791","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":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.15302","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100353160","display_name":"Chang Liu","orcid":"https://orcid.org/0000-0001-6980-7791"},"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":true,"raw_author_name":"Chang Liu","raw_affiliation_strings":["School of Electrical and Electronic Engineering (EEE), Nanyang Technological University, Jurong West, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering (EEE), Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036631624","display_name":"Henghui Ding","orcid":"https://orcid.org/0000-0003-4868-6526"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Henghui Ding","raw_affiliation_strings":["Computer Vision Laboratory (CVL), ETH Z&#x00FC;rich, Z&#x00FC;rich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Computer Vision Laboratory (CVL), ETH Z&#x00FC;rich, Z&#x00FC;rich, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074865219","display_name":"Yulun Zhang","orcid":"https://orcid.org/0000-0002-2288-5079"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yulun Zhang","raw_affiliation_strings":["Computer Vision Laboratory (CVL), ETH Z&#x00FC;rich, Z&#x00FC;rich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Computer Vision Laboratory (CVL), ETH Z&#x00FC;rich, Z&#x00FC;rich, Switzerland","institution_ids":[]}]},{"author_position":"last","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 (EEE), Nanyang Technological University, Jurong West, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering (EEE), Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100353160"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":7.6224,"has_fulltext":true,"cited_by_count":63,"citation_normalized_percentile":{"value":0.98209802,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"3054","last_page":"3065"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9937999844551086,"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/T10028","display_name":"Topic Modeling","score":0.991599977016449,"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/computer-science","display_name":"Computer science","score":0.7349215745925903},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6419621706008911},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.571255624294281},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.564335286617279},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5479724407196045},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5197479724884033},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5130873918533325},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5045708417892456},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4994223117828369},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49160322546958923},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4520171284675598},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43958523869514465},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08519530296325684},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08326402306556702}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7349215745925903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6419621706008911},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.571255624294281},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.564335286617279},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5479724407196045},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5197479724884033},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5130873918533325},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5045708417892456},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4994223117828369},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49160322546958923},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4520171284675598},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43958523869514465},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08519530296325684},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08326402306556702},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tip.2023.3277791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3277791","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:37220044","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37220044","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},{"id":"pmh:oai:arXiv.org:2305.15302","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.15302","pdf_url":"https://arxiv.org/pdf/2305.15302","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.15302","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.15302","pdf_url":"https://arxiv.org/pdf/2305.15302","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"score":0.6000000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4377711491.pdf"},"referenced_works_count":84,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1861492603","https://openalex.org/W1903029394","https://openalex.org/W2144960104","https://openalex.org/W2250539671","https://openalex.org/W2302548814","https://openalex.org/W2489434015","https://openalex.org/W2558535589","https://openalex.org/W2571175805","https://openalex.org/W2583360688","https://openalex.org/W2605127024","https://openalex.org/W2606746036","https://openalex.org/W2770129969","https://openalex.org/W2779827764","https://openalex.org/W2798556392","https://openalex.org/W2798791840","https://openalex.org/W2876852810","https://openalex.org/W2896457183","https://openalex.org/W2899002405","https://openalex.org/W2904910963","https://openalex.org/W2948080074","https://openalex.org/W2963037989","https://openalex.org/W2963091558","https://openalex.org/W2963109634","https://openalex.org/W2963735856","https://openalex.org/W2964345792","https://openalex.org/W2965373594","https://openalex.org/W2980088508","https://openalex.org/W2984121207","https://openalex.org/W2987734933","https://openalex.org/W2989684653","https://openalex.org/W2999725795","https://openalex.org/W3004019157","https://openalex.org/W3020827971","https://openalex.org/W3030520226","https://openalex.org/W3034325957","https://openalex.org/W3034692043","https://openalex.org/W3034772468","https://openalex.org/W3035097537","https://openalex.org/W3093025045","https://openalex.org/W3094502228","https://openalex.org/W3108748824","https://openalex.org/W3108925098","https://openalex.org/W3110435696","https://openalex.org/W3126792443","https://openalex.org/W3138516171","https://openalex.org/W3159619744","https://openalex.org/W3166396011","https://openalex.org/W3169998662","https://openalex.org/W3172522282","https://openalex.org/W3178075329","https://openalex.org/W3187664142","https://openalex.org/W3201770677","https://openalex.org/W3211490618","https://openalex.org/W3213165621","https://openalex.org/W3216551675","https://openalex.org/W4200631575","https://openalex.org/W4221149230","https://openalex.org/W4224988000","https://openalex.org/W4307504011","https://openalex.org/W4308909683","https://openalex.org/W4312517005","https://openalex.org/W4312543911","https://openalex.org/W4312919100","https://openalex.org/W4319323799","https://openalex.org/W4322615526","https://openalex.org/W4327534052","https://openalex.org/W4366567811","https://openalex.org/W4385245566","https://openalex.org/W4386066080","https://openalex.org/W4386075822","https://openalex.org/W4386076142","https://openalex.org/W6631190155","https://openalex.org/W6639102338","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6768730002","https://openalex.org/W6778485988","https://openalex.org/W6789753369","https://openalex.org/W6791353385","https://openalex.org/W6797399245","https://openalex.org/W6798505901","https://openalex.org/W6798837711"],"related_works":["https://openalex.org/W3000097931","https://openalex.org/W2354322770","https://openalex.org/W4237547500","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W4243305035","https://openalex.org/W1537496349","https://openalex.org/W2379407973","https://openalex.org/W2350267540"],"abstract_inverted_index":{"We":[0],"address":[1,100],"the":[2,15,32,37,42,50,78,83,90,96,121,156,165,177],"problem":[3],"of":[4],"referring":[5,182],"image":[6,183],"segmentation":[7,184],"that":[8,116,171],"aims":[9],"to":[10,28,80,94,136,154],"generate":[11],"a":[12,19],"mask":[13,92],"for":[14,31,53,89],"object":[16,34],"specified":[17],"by":[18,35,73],"natural":[20],"language":[21,51,62,143,157],"expression.":[22],"Many":[23],"recent":[24],"works":[25],"utilize":[26],"Transformer":[27,47],"extract":[29,95],"features":[30,63],"target":[33],"aggregating":[36],"attended":[38],"visual":[39],"regions.":[40],"However,":[41],"generic":[43],"attention":[44,54],"mechanism":[45],"in":[46,64,164],"only":[48],"uses":[49],"input":[52,123],"weight":[55],"calculation,":[56],"which":[57,76],"does":[58],"not":[59],"explicitly":[60],"fuse":[61,118],"its":[65,68],"output.":[66],"Thus,":[67],"output":[69,97],"feature":[70],"is":[71],"dominated":[72],"vision":[74,145],"information,":[75,85],"limits":[77],"model":[79],"comprehensively":[81],"understand":[82],"multi-modal":[84],"and":[86,109,139,144,179],"brings":[87],"uncertainty":[88],"subsequent":[91],"decoder":[93],"mask.":[98],"To":[99],"this":[101],"issue,":[102],"we":[103,129,148],"propose":[104,131],"Multi-Modal":[105,110],"Mutual":[106,111],"Attention":[107],"(M3Att)":[108],"Decoder":[112],"(":[113],"M<sup>3</sup>Dec":[114,127],")":[115],"better":[117],"information":[119,158],"from":[120,159],"two":[122],"modalities.":[124],"Based":[125],"on":[126,186],",":[128],"further":[130],"Iterative":[132],"Multi-modal":[133],"Interaction":[134],"(IMI)":[135],"allow":[137],"continuous":[138],"in-depth":[140],"interactions":[141],"between":[142],"features.":[146],"Furthermore,":[147],"introduce":[149],"Language":[150],"Feature":[151],"Reconstruction":[152],"(LFR)":[153],"prevent":[155],"being":[160],"lost":[161],"or":[162],"distorted":[163],"extracted":[166],"feature.":[167],"Extensive":[168],"experiments":[169],"show":[170],"our":[172],"proposed":[173],"approach":[174],"significantly":[175],"improves":[176],"baseline":[178],"outperforms":[180],"state-of-the-art":[181],"methods":[185],"RefCOCO":[187],"series":[188],"datasets":[189],"consistently.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}