{"id":"https://openalex.org/W4411269934","doi":"https://doi.org/10.1109/tcsvt.2025.3579580","title":"Distilling Hierarchical Knowledge From Multimodal Fusion for Unimodal Image Segmentation","display_name":"Distilling Hierarchical Knowledge From Multimodal Fusion for Unimodal Image Segmentation","publication_year":2025,"publication_date":"2025-06-13","ids":{"openalex":"https://openalex.org/W4411269934","doi":"https://doi.org/10.1109/tcsvt.2025.3579580"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3579580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3579580","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":null,"display_name":"Yujia Sun","orcid":"https://orcid.org/0009-0001-0929-2164"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yujia Sun","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037310802","display_name":"Weisheng Dong","orcid":"https://orcid.org/0000-0002-9632-985X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weisheng Dong","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084110389","display_name":"Shuaibo Wang","orcid":"https://orcid.org/0009-0006-8523-0842"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuaibo Wang","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032693575","display_name":"Peng Wu","orcid":"https://orcid.org/0000-0003-2938-6798"},"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":"Peng Wu","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087490575","display_name":"Mingtao Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingtao Feng","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354039","display_name":"Xin Li","orcid":"https://orcid.org/0000-0003-2067-2763"},"institutions":[{"id":"https://openalex.org/I392282","display_name":"University at Albany, State University of New York","ror":"https://ror.org/012zs8222","country_code":"US","type":"education","lineage":["https://openalex.org/I392282"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["Department of Computer Science, University at Albany, Albany, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University at Albany, Albany, NY, USA","institution_ids":["https://openalex.org/I392282"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101549504","display_name":"Guangming Shi","orcid":"https://orcid.org/0000-0003-2179-3292"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangming Shi","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":2.4362,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89239394,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"35","issue":"12","first_page":"11797","last_page":"11809"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.8198999762535095,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.8198999762535095,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.7397000193595886,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.7077000141143799,"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/computer-science","display_name":"Computer science","score":0.665217936038971},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.6499280333518982},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6478123664855957},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5234129428863525},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.4839527904987335},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4540565311908722},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.438742458820343},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43744492530822754},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4233188033103943}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.665217936038971},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.6499280333518982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6478123664855957},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5234129428863525},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.4839527904987335},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4540565311908722},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.438742458820343},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43744492530822754},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4233188033103943},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3579580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3579580","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":[{"id":"https://openalex.org/G1465847274","display_name":null,"funder_award_id":"62302369","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G712080188","display_name":null,"funder_award_id":"61991451","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G904860190","display_name":null,"funder_award_id":"62472336","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":71,"referenced_works":["https://openalex.org/W1536587585","https://openalex.org/W1563797521","https://openalex.org/W1708141795","https://openalex.org/W1821462560","https://openalex.org/W1964641132","https://openalex.org/W1976303724","https://openalex.org/W1996278907","https://openalex.org/W2015264084","https://openalex.org/W2028555274","https://openalex.org/W2054273865","https://openalex.org/W2091484864","https://openalex.org/W2108598243","https://openalex.org/W2121219287","https://openalex.org/W2133665775","https://openalex.org/W2136401825","https://openalex.org/W2142060261","https://openalex.org/W2146353910","https://openalex.org/W2182332322","https://openalex.org/W2559870345","https://openalex.org/W2738292856","https://openalex.org/W2767512561","https://openalex.org/W2774839435","https://openalex.org/W2798018774","https://openalex.org/W2798987894","https://openalex.org/W2891029880","https://openalex.org/W2894994475","https://openalex.org/W2928559779","https://openalex.org/W2954054736","https://openalex.org/W2971071255","https://openalex.org/W3035467948","https://openalex.org/W3041991648","https://openalex.org/W3046194589","https://openalex.org/W3089682612","https://openalex.org/W3103264598","https://openalex.org/W3134566480","https://openalex.org/W3138516171","https://openalex.org/W3139244260","https://openalex.org/W3158080681","https://openalex.org/W3198062544","https://openalex.org/W3206439726","https://openalex.org/W3207919963","https://openalex.org/W4200635035","https://openalex.org/W4206713196","https://openalex.org/W4210393880","https://openalex.org/W4220893768","https://openalex.org/W4283732315","https://openalex.org/W4296913506","https://openalex.org/W4308310215","https://openalex.org/W4312396555","https://openalex.org/W4312402232","https://openalex.org/W4312594135","https://openalex.org/W4313139043","https://openalex.org/W4313267411","https://openalex.org/W4313555022","https://openalex.org/W4364302354","https://openalex.org/W4376131895","https://openalex.org/W4379140782","https://openalex.org/W4379209584","https://openalex.org/W4381300351","https://openalex.org/W4382119107","https://openalex.org/W4382119971","https://openalex.org/W4383503983","https://openalex.org/W4385768166","https://openalex.org/W4386065698","https://openalex.org/W4387968982","https://openalex.org/W4390727645","https://openalex.org/W4390873110","https://openalex.org/W4392908457","https://openalex.org/W4393240973","https://openalex.org/W4396920227","https://openalex.org/W4398224523"],"related_works":["https://openalex.org/W2788731446","https://openalex.org/W2204403038","https://openalex.org/W3152170969","https://openalex.org/W2379054866","https://openalex.org/W2370195708","https://openalex.org/W1490651872","https://openalex.org/W2139242969","https://openalex.org/W2284201331","https://openalex.org/W2095903272","https://openalex.org/W1989561795"],"abstract_inverted_index":{"The":[0],"application":[1],"of":[2,16,35,58,79,97,124],"multimodal":[3,73,136,168,203,233,247,256],"image":[4,119,137,241,257],"fusion":[5,20,57,138,169,258],"has":[6],"become":[7],"increasingly":[8],"widespread":[9],"across":[10],"various":[11],"fields":[12],"in":[13,174],"the":[14,33,56,93,122,149,155,175,184,195,202,207,224,236],"era":[15],"deep":[17],"learning.":[18],"Existing":[19],"methods":[21],"integrate":[22],"infrared":[23,59],"and":[24,31,47,60,75,163,170,197,220,243,249,259],"visible":[25,61],"images":[26,80,151],"to":[27,92,129,193,206,255],"provide":[28],"complementary":[29],"content":[30],"enhance":[32],"robustness":[34],"complex":[36],"real-world":[37],"scenes":[38],"for":[39,117,240],"high-level":[40,52,144],"visual":[41,53,145],"tasks,":[42],"such":[43,68],"as":[44,131,139,178],"semantic":[45,65],"segmentation":[46,120,171,244,260],"object":[48],"detection.":[49],"In":[50,183],"return,":[51],"tasks":[54,146],"facilitate":[55],"by":[62],"providing":[63],"mid-level":[64],"information.":[66],"However,":[67],"frameworks":[69],"rely":[70],"heavily":[71],"on":[72,214],"data":[74],"require":[76],"strict":[77],"registration":[78],"from":[81,135,201],"different":[82],"modalities":[83,99],"before":[84],"fusion,":[85],"seriously":[86],"limiting":[87],"their":[88],"practical":[89],"applications":[90],"due":[91],"common":[94],"realistic":[95],"situations":[96],"missing":[98],"or":[100],"misregistration.":[101],"To":[102],"move":[103],"beyond":[104],"this":[105],"limitation,":[106],"we":[107,164,187],"propose":[108],"a":[109,166,179,189],"novel":[110],"hierarchical":[111,190,226],"knowledge":[112,200,227,234],"distillation":[113,191,228],"(HKD)":[114],"framework":[115,127,229],"tailored":[116],"unimodal":[118,150,208,237],"with":[121],"guidance":[123],"multi-modality.":[125],"This":[126],"aims":[128],"retain":[130],"much":[132],"diverse":[133],"information":[134],"possible,":[140],"thereby":[141],"enhancing":[142],"downstream":[143],"when":[147],"only":[148],"are":[152],"available":[153],"during":[154],"inference":[156],"phase.":[157],"Our":[158],"proposed":[159,225],"method":[160,192],"is":[161],"two-stage,":[162],"construct":[165],"robust":[167],"interaction":[172],"network":[173],"first":[176],"stage":[177],"powerful":[180],"teacher":[181,204],"model.":[182,210],"second":[185],"stage,":[186],"design":[188],"transfer":[194],"fused":[196],"segmented":[198],"multi-layer":[199],"model":[205,239],"student":[209,238],"Extensive":[211],"experimental":[212],"results":[213,253],"two":[215],"public":[216],"datasets,":[217],"i.e.,":[218],"MFNet":[219],"FMB,":[221],"demonstrate":[222],"that":[223],"can":[230],"effectively":[231],"transfuse":[232],"into":[235],"enhancement":[242],"under":[245],"incomplete":[246],"conditions,":[248],"achieves":[250],"considerably":[251],"competitive":[252],"compared":[254],"models.":[261]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}