{"id":"https://openalex.org/W4391164254","doi":"https://doi.org/10.1109/tmm.2024.3358085","title":"CM-MaskSD: Cross-Modality Masked Self-Distillation for Referring Image Segmentation","display_name":"CM-MaskSD: Cross-Modality Masked Self-Distillation for Referring Image Segmentation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391164254","doi":"https://doi.org/10.1109/tmm.2024.3358085"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3358085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3358085","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5100755188","display_name":"Wenxuan Wang","orcid":"https://orcid.org/0000-0002-9022-1370"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenxuan Wang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101777772","display_name":"Xingjian He","orcid":"https://orcid.org/0000-0001-5396-6253"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingjian He","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103168973","display_name":"Yisi Zhang","orcid":"https://orcid.org/0009-0001-0165-5346"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yisi Zhang","raw_affiliation_strings":["School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040424302","display_name":"Longteng Guo","orcid":"https://orcid.org/0000-0002-4340-4000"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longteng Guo","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101621550","display_name":"Jiachen Shen","orcid":"https://orcid.org/0000-0003-1323-7560"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiachen Shen","raw_affiliation_strings":["School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074215202","display_name":"Jiangyun Li","orcid":"https://orcid.org/0000-0003-2288-7901"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyun Li","raw_affiliation_strings":["School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108392430","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-0903-9131"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100755188"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"],"apc_list":null,"apc_paid":null,"fwci":4.6548,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.95752707,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"26","issue":null,"first_page":"6906","last_page":"6916"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9975000023841858,"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":0.9975000023841858,"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":0.972100019454956,"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/T10028","display_name":"Topic Modeling","score":0.9602000117301941,"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":0.7939640283584595},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.6969107389450073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6442714333534241},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5814470052719116},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5617579221725464},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.497071772813797},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4807743430137634},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.47619354724884033},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45865604281425476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7939640283584595},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.6969107389450073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6442714333534241},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5814470052719116},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5617579221725464},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.497071772813797},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4807743430137634},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.47619354724884033},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45865604281425476},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"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":1,"locations":[{"id":"doi:10.1109/tmm.2024.3358085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3358085","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1283858192","display_name":null,"funder_award_id":"U21B2043","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1508456709","display_name":null,"funder_award_id":"62102416","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6025668223","display_name":null,"funder_award_id":"42201386","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":66,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2064675550","https://openalex.org/W2161236525","https://openalex.org/W2302548814","https://openalex.org/W2489434015","https://openalex.org/W2605127024","https://openalex.org/W2798556392","https://openalex.org/W2876852810","https://openalex.org/W2894964039","https://openalex.org/W2896457183","https://openalex.org/W2952793010","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W2965373594","https://openalex.org/W2973233205","https://openalex.org/W2980088508","https://openalex.org/W3003423830","https://openalex.org/W3023463084","https://openalex.org/W3034325957","https://openalex.org/W3034692043","https://openalex.org/W3035097537","https://openalex.org/W3093025045","https://openalex.org/W3094502228","https://openalex.org/W3099166112","https://openalex.org/W3108748824","https://openalex.org/W3156800342","https://openalex.org/W3157386596","https://openalex.org/W3157413304","https://openalex.org/W3170863103","https://openalex.org/W3171547673","https://openalex.org/W3172522282","https://openalex.org/W3187664142","https://openalex.org/W3193426425","https://openalex.org/W3201770677","https://openalex.org/W3216551675","https://openalex.org/W4200631575","https://openalex.org/W4226058394","https://openalex.org/W4281571140","https://openalex.org/W4281917203","https://openalex.org/W4282011138","https://openalex.org/W4287824654","https://openalex.org/W4295312788","https://openalex.org/W4301914798","https://openalex.org/W4309181071","https://openalex.org/W4312543911","https://openalex.org/W4312804044","https://openalex.org/W4312980183","https://openalex.org/W4313156423","https://openalex.org/W4315705717","https://openalex.org/W4321593231","https://openalex.org/W4361991106","https://openalex.org/W4385245566","https://openalex.org/W4386072286","https://openalex.org/W4392449449","https://openalex.org/W6725193200","https://openalex.org/W6766673545","https://openalex.org/W6766978945","https://openalex.org/W6771917389","https://openalex.org/W6784333009","https://openalex.org/W6791353385","https://openalex.org/W6796761347","https://openalex.org/W6797397777","https://openalex.org/W6838614222","https://openalex.org/W6839143948","https://openalex.org/W6845452229","https://openalex.org/W6848688062"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W2364381299","https://openalex.org/W2374430585","https://openalex.org/W3144423903","https://openalex.org/W2377397762","https://openalex.org/W2361654993","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Referring":[0],"image":[1,18,34],"segmentation":[2,122,145],"(RIS)":[3],"is":[4],"a":[5,13,21,91,134],"fundamental":[6],"vision-language":[7,47],"task":[8,176],"that":[9],"intends":[10],"to":[11,27,114],"segment":[12],"desired":[14],"object":[15],"from":[16,111],"an":[17],"based":[19],"on":[20,165],"given":[22],"natural":[23],"language":[24],"expression.":[25],"Due":[26],"the":[28,75,80,104,143,148,160,174,179],"essentially":[29],"distinct":[30],"data":[31],"properties":[32],"between":[33,142],"and":[35,69,89,147,153],"text,":[36],"most":[37],"of":[38,82,107,181],"existing":[39],"methods":[40],"either":[41],"introduce":[42],"complex":[43],"designs":[44],"towards":[45],"fine-grained":[46,71,116],"alignment":[48,73,110,119],"or":[49,58,64],"lack":[50],"required":[51],"dense":[52],"alignment,":[53],"resulting":[54],"in":[55,74,99,133],"scalability":[56],"issues":[57],"mis-segmentation":[59],"problems":[60],"such":[61],"as":[62],"over-":[63],"under-segmentation.":[65],"To":[66],"achieve":[67],"effective":[68],"efficient":[70],"feature":[72,118],"RIS":[76,175],"task,":[77],"we":[78],"explore":[79],"potential":[81],"masked":[83,94,150],"multimodal":[84,161],"modeling":[85],"coupled":[86],"with":[87],"self-distillation":[88,95,151],"propose":[90],"novel":[92],"cross-modality":[93],"framework":[96,127,184],"named":[97],"CM-MaskSD,":[98],"which":[100],"our":[101,125,182],"method":[102],"inherits":[103],"transferred":[105],"knowledge":[106],"image-text":[108],"semantic":[109],"CLIP":[112],"model":[113,131],"realize":[115],"patch-word":[117],"for":[120,158,173],"better":[121],"accuracy.":[123],"Moreover,":[124],"CM-MaskSD":[126],"can":[128],"considerably":[129],"boost":[130],"performance":[132],"nearly":[135],"parameter-free":[136],"manner,":[137],"since":[138],"it":[139],"shares":[140],"weights":[141],"main":[144],"branch":[146],"introduced":[149],"branches,":[152],"solely":[154],"introduces":[155],"negligible":[156],"parameters":[157],"coordinating":[159],"features.":[162],"Comprehensive":[163],"experiments":[164],"three":[166],"benchmark":[167],"datasets":[168],"(ie":[169],"RefCOCO,":[170],"RefCOCO+,":[171],"G-Ref)":[172],"convincingly":[177],"demonstrate":[178],"superiority":[180],"proposed":[183],"over":[185],"previous":[186],"state-of-the-art":[187],"methods.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":5}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}