{"id":"https://openalex.org/W7138090563","doi":"https://doi.org/10.1609/aaai.v40i13.38033","title":"CHARM: Collaborative Harmonization Across Arbitrary Modalities for Modality-Agnostic Semantic Segmentation","display_name":"CHARM: Collaborative Harmonization Across Arbitrary Modalities for Modality-Agnostic Semantic Segmentation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138090563","doi":"https://doi.org/10.1609/aaai.v40i13.38033"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i13.38033","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38033","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i13.38033","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032066259","display_name":"Lekang Wen","orcid":"https://orcid.org/0009-0000-6222-4243"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lekang Wen","raw_affiliation_strings":["Wuhan University"],"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129694621","display_name":"Jing Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Wuhan University"],"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129733638","display_name":"Liang Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115513","display_name":"Xi\u2019an University","ror":"https://ror.org/01zzmf129","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210115513"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Liao","raw_affiliation_strings":["Xi'an University of Electronic Science and Technology"],"affiliations":[{"raw_affiliation_string":"Xi'an University of Electronic Science and Technology","institution_ids":["https://openalex.org/I4210115513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129697871","display_name":"Jiajun Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Chen","raw_affiliation_strings":["Wuhan University"],"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129667840","display_name":"Mi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mi Wang","raw_affiliation_strings":["Wuhan University"],"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5032066259"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39477612,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"13","first_page":"10603","last_page":"10611"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.483599990606308,"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":0.483599990606308,"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":0.34709998965263367,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.03280000016093254,"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/modalities","display_name":"Modalities","score":0.5924999713897705},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.565500020980835},{"id":"https://openalex.org/keywords/complementarity","display_name":"Complementarity (molecular biology)","score":0.5630000233650208},{"id":"https://openalex.org/keywords/harmonization","display_name":"Harmonization","score":0.4453999996185303},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4262999892234802},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4262000024318695},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4244999885559082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7602999806404114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5975000262260437},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5924999713897705},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.565500020980835},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.5630000233650208},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46209999918937683},{"id":"https://openalex.org/C2779962950","wikidata":"https://www.wikidata.org/wiki/Q5659376","display_name":"Harmonization","level":2,"score":0.4453999996185303},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4262999892234802},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4244999885559082},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33320000767707825},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C60115397","wikidata":"https://www.wikidata.org/wiki/Q5188732","display_name":"Crossmodal","level":4,"score":0.32359999418258667},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i13.38033","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38033","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i13.38033","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38033","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modality-agnostic":[0],"Semantic":[1],"Segmentation":[2],"(MaSS)":[3],"aims":[4],"to":[5,24,57,91,149],"achieve":[6,25,42],"robust":[7],"scene":[8],"understanding":[9],"across":[10,122],"arbitrary":[11],"combinations":[12],"of":[13,33],"input":[14],"modality.":[15],"Existing":[16],"methods":[17],"typically":[18],"rely":[19],"on":[20,137],"explicit":[21],"feature":[22],"alignment":[23,75],"modal":[26],"homogenization,":[27,47],"which":[28],"dilutes":[29],"the":[30,132,138,144],"distinctive":[31],"strengths":[32],"each":[34,89],"modality":[35],"and":[36,86,112,125],"destroys":[37],"their":[38],"inherent":[39],"complementarity.":[40],"To":[41],"cooperative":[43],"harmonization":[44],"rather":[45],"than":[46],"we":[48],"propose":[49],"CHARM,":[50],"a":[51],"novel":[52],"complementary":[53,109],"learning":[54,111],"framework":[55],"designed":[56],"implicitly":[58],"align":[59],"content":[60],"while":[61],"preserving":[62],"modality-specific":[63,119],"advantages":[64],"through":[65,76],"two":[66],"components:":[67],"(1)":[68],"Mutual":[69],"Perception":[70],"Unit":[71],"(MPU),":[72],"enabling":[73,151],"implicit":[74],"window-based":[77],"cross-modal":[78,152],"interaction,":[79],"where":[80],"modalities":[81],"serve":[82],"as":[83],"both":[84],"queries":[85],"contexts":[87],"for":[88,108,117,154],"other":[90],"discover":[92],"modality-interactive":[93],"correspondences;":[94],"(2)":[95],"A":[96],"dual-path":[97],"optimization":[98],"strategy":[99],"that":[100,128],"decouples":[101],"training":[102],"into":[103],"Collaborative":[104],"Learning":[105],"Strategy":[106,115],"(CoL)":[107],"fusion":[110],"Individual":[113],"Enhancement":[114],"(InE)":[116],"protected":[118],"optimization.":[120],"Experiments":[121],"multiple":[123],"datasets":[124],"backbones":[126],"indicate":[127],"CHARM":[129],"consistently":[130],"outperform":[131],"baselines,":[133],"with":[134],"significant":[135],"increment":[136],"fragile":[139],"modalities.":[140],"This":[141],"work":[142],"shifts":[143],"focus":[145],"from":[146],"model":[147],"homogenization":[148],"harmonization,":[150],"complementarity":[153],"true":[155],"harmony":[156],"in":[157],"diversity.":[158]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}