{"id":"https://openalex.org/W7164806818","doi":"https://doi.org/10.1145/3805622.3810817","title":"Agglomerative Model Meets Multi-Scale Adaptive Fusion for Cross-Modal Unsupervised Domain Adaptation","display_name":"Agglomerative Model Meets Multi-Scale Adaptive Fusion for Cross-Modal Unsupervised Domain Adaptation","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164806818","doi":"https://doi.org/10.1145/3805622.3810817"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810817","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810817","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810817","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101618778","display_name":"Zhixun Wang","orcid":"https://orcid.org/0009-0009-0701-0192"},"institutions":[{"id":"https://openalex.org/I135714990","display_name":"North University of China","ror":"https://ror.org/047bp1713","country_code":"CN","type":"education","lineage":["https://openalex.org/I135714990"]},{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixun Wang","raw_affiliation_strings":["School of Computer Science and Technology, North University of China, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Machine Vision & Virtual Reality, Taiyuan, Shanxi, China"],"raw_orcid":"https://orcid.org/0009-0005-2049-3089","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, North University of China, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Machine Vision & Virtual Reality, Taiyuan, Shanxi, China","institution_ids":["https://openalex.org/I181877577","https://openalex.org/I135714990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009855115","display_name":"Liqun Kuang","orcid":"https://orcid.org/0000-0003-3276-5748"},"institutions":[{"id":"https://openalex.org/I135714990","display_name":"North University of China","ror":"https://ror.org/047bp1713","country_code":"CN","type":"education","lineage":["https://openalex.org/I135714990"]},{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqun Kuang","raw_affiliation_strings":["School of Computer Science and Technology, North University of China, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Machine Vision & Virtual Reality, Taiyuan, Shanxi, China"],"raw_orcid":"https://orcid.org/0000-0003-3276-5748","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, North University of China, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Machine Vision & Virtual Reality, Taiyuan, Shanxi, China","institution_ids":["https://openalex.org/I181877577","https://openalex.org/I135714990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115602084","display_name":"Song Wang","orcid":"https://orcid.org/0000-0003-1252-8091"},"institutions":[{"id":"https://openalex.org/I135714990","display_name":"North University of China","ror":"https://ror.org/047bp1713","country_code":"CN","type":"education","lineage":["https://openalex.org/I135714990"]},{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Wang","raw_affiliation_strings":["School of Computer Science and Technology, North University of China, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Machine Vision & Virtual Reality, Taiyuan, Shanxi, China"],"raw_orcid":"https://orcid.org/0009-0004-4463-8484","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, North University of China, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Machine Vision & Virtual Reality, Taiyuan, Shanxi, China","institution_ids":["https://openalex.org/I181877577","https://openalex.org/I135714990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066304561","display_name":"Shichao Jiao","orcid":"https://orcid.org/0000-0002-2589-3533"},"institutions":[{"id":"https://openalex.org/I135714990","display_name":"North University of China","ror":"https://ror.org/047bp1713","country_code":"CN","type":"education","lineage":["https://openalex.org/I135714990"]},{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shichao Jiao","raw_affiliation_strings":["School of Computer Science and Technology, North University of China, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Machine Vision & Virtual Reality, Taiyuan, Shanxi, China"],"raw_orcid":"https://orcid.org/0000-0002-2589-3533","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, North University of China, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Machine Vision & Virtual Reality, Taiyuan, Shanxi, China","institution_ids":["https://openalex.org/I181877577","https://openalex.org/I135714990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046023143","display_name":"Zhongyu Chen","orcid":"https://orcid.org/0000-0002-9429-6759"},"institutions":[{"id":"https://openalex.org/I135714990","display_name":"North University of China","ror":"https://ror.org/047bp1713","country_code":"CN","type":"education","lineage":["https://openalex.org/I135714990"]},{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyu Chen","raw_affiliation_strings":["School of Computer Science and Technology, North University of China, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Machine Vision & Virtual Reality, Taiyuan, Shanxi, China"],"raw_orcid":"https://orcid.org/0009-0002-1198-8539","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, North University of China, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Machine Vision & Virtual Reality, Taiyuan, Shanxi, China","institution_ids":["https://openalex.org/I181877577","https://openalex.org/I135714990"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034256540","display_name":"Fengguang Xiong","orcid":"https://orcid.org/0000-0003-3596-6457"},"institutions":[{"id":"https://openalex.org/I135714990","display_name":"North University of China","ror":"https://ror.org/047bp1713","country_code":"CN","type":"education","lineage":["https://openalex.org/I135714990"]},{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengguang Xiong","raw_affiliation_strings":["School of Computer Science and Technology, North University of China, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Machine Vision & Virtual Reality, Taiyuan, Shanxi, China"],"raw_orcid":"https://orcid.org/0000-0003-3596-6457","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, North University of China, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Machine Vision & Virtual Reality, Taiyuan, Shanxi, China","institution_ids":["https://openalex.org/I181877577","https://openalex.org/I135714990"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94617399,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"940","last_page":"948"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9796000123023987,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9796000123023987,"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/T11448","display_name":"Face recognition and analysis","score":0.006099999882280827,"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":0.004000000189989805,"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/encoder","display_name":"Encoder","score":0.6523000001907349},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6241000294685364},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5726000070571899},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5683000087738037},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5012999773025513},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.45410001277923584},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.43369999527931213},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.4309999942779541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7735000252723694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6869000196456909},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6523000001907349},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6241000294685364},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5726000070571899},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5683000087738037},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5012999773025513},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.45410001277923584},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.43369999527931213},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.4309999942779541},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42250001430511475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37929999828338623},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3199999928474426},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C142816647","wikidata":"https://www.wikidata.org/wiki/Q5573018","display_name":"Glyph (data visualization)","level":3,"score":0.26759999990463257},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810817","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810817","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810817","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810817","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2963073217","https://openalex.org/W2964057616","https://openalex.org/W2972285644","https://openalex.org/W2991216808","https://openalex.org/W3035574168","https://openalex.org/W3035750252","https://openalex.org/W3080980548","https://openalex.org/W3163179572","https://openalex.org/W3201726317","https://openalex.org/W3216568609","https://openalex.org/W4304092477","https://openalex.org/W4304092631","https://openalex.org/W4313854933","https://openalex.org/W4385801269","https://openalex.org/W4388191323","https://openalex.org/W4388223553","https://openalex.org/W4399768898","https://openalex.org/W4401147979","https://openalex.org/W4402780115","https://openalex.org/W4403780606","https://openalex.org/W4405179183","https://openalex.org/W4407948693","https://openalex.org/W4409525418","https://openalex.org/W4412871044","https://openalex.org/W4413145796","https://openalex.org/W4413146259","https://openalex.org/W4413147599","https://openalex.org/W4413147814","https://openalex.org/W4413402787","https://openalex.org/W4415708452","https://openalex.org/W4415795996"],"related_works":[],"abstract_inverted_index":{"Although":[0],"cross-modal":[1],"unsupervised":[2],"domain":[3,31],"adaptation":[4],"(UDA)":[5],"has":[6],"emerged":[7],"as":[8,67],"an":[9,45],"effective":[10],"means":[11],"to":[12,23,115,128],"reduce":[13],"annotation":[14],"costs":[15],"for":[16,75],"semantic":[17,179],"segmentation,":[18],"existing":[19],"approaches":[20],"often":[21],"struggle":[22],"learn":[24],"semantically":[25],"consistent,":[26],"domain-invariant":[27],"representations":[28,74],"under":[29,88],"severe":[30],"shifts.":[32],"To":[33],"narrow":[34],"this":[35],"representational":[36],"gap,":[37],"we":[38,60],"develop":[39],"a":[40,53],"new":[41],"strategy":[42],"that":[43,96],"couples":[44],"agglomerative":[46],"visual":[47,63],"foundation":[48,64],"model\u2013based":[49],"encoding":[50],"paradigm":[51],"with":[52],"Multi-scale":[54],"Adaptive":[55],"Fusion":[56],"Module":[57],"(MAFM).":[58],"Specifically,":[59],"adopt":[61],"the":[62,68,80,104,117,134,162,182,185],"model":[65],"C-RADIOv3":[66],"2D":[69,106,163],"encoder":[70,81],"and":[71,108,112,140,151,164,177],"tailor":[72],"its":[73],"dense":[76],"prediction":[77],"while":[78],"keeping":[79],"frozen,":[82],"which":[83],"yields":[84],"robust,":[85],"high-quality":[86],"features":[87,107],"varying":[89],"image":[90],"resolutions.":[91],"We":[92],"further":[93,169],"introduce":[94],"MAFM":[95,123],"builds":[97],"parallel":[98],"multi-resolution":[99],"branches":[100],"on":[101,161],"top":[102],"of":[103,137,174,184],"enhanced":[105],"leverages":[109],"dynamic":[110],"large":[111],"small-kernel":[113],"convolutions":[114],"broaden":[116],"receptive":[118],"field.":[119],"After":[120],"cross-scale":[121],"alignment,":[122],"performs":[124],"per-location":[125],"adaptive":[126],"reweighting":[127],"fuse":[129],"complementary":[130],"cues,":[131],"thereby":[132],"strengthening":[133],"joint":[135],"representation":[136],"global":[138],"semantics":[139],"fine-grained":[141],"boundaries.":[142],"Experiments":[143],"across":[144],"multiple":[145],"scenarios,":[146],"including":[147],"USA":[148],"\u2192":[149,153],"Singapore":[150],"A2D2":[152],"SemanticKITTI,":[154],"demonstrate":[155],"consistent":[156],"improvements":[157],"over":[158],"strong":[159],"baselines":[160],"fusion":[165],"branches;":[166],"qualitative":[167],"visualizations":[168],"reveal":[170],"notably":[171],"better":[172],"recognition":[173],"small-object":[175],"classes":[176],"sharper":[178],"boundaries,":[180],"corroborating":[181],"effectiveness":[183],"proposed":[186],"method.":[187]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}