{"id":"https://openalex.org/W4403780606","doi":"https://doi.org/10.1145/3664647.3680582","title":"CLIP2UDA: Making Frozen CLIP Reward Unsupervised Domain Adaptation in 3D Semantic Segmentation","display_name":"CLIP2UDA: Making Frozen CLIP Reward Unsupervised Domain Adaptation in 3D Semantic Segmentation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780606","doi":"https://doi.org/10.1145/3664647.3680582"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680582","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5072449190","display_name":"Yao Wu","orcid":"https://orcid.org/0000-0003-0227-5641"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Wu","raw_affiliation_strings":["School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0003-0227-5641","affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081948656","display_name":"Mingwei Xing","orcid":"https://orcid.org/0000-0002-2728-4096"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingwei Xing","raw_affiliation_strings":["Institute of Artificial Intelligence, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-2728-4096","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667178","display_name":"Yachao Zhang","orcid":"https://orcid.org/0000-0002-6153-5004"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yachao Zhang","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6153-5004","affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110042813","display_name":"Yuan Xie","orcid":"https://orcid.org/0000-0001-6945-7437"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Xie","raw_affiliation_strings":["East China Normal University & Chongqing Institute of East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6945-7437","affiliations":[{"raw_affiliation_string":"East China Normal University & Chongqing Institute of East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076485255","display_name":"Yanyun Qu","orcid":"https://orcid.org/0000-0002-8926-4162"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyun Qu","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-8926-4162","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5333,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.94476992,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8662","last_page":"8671"},"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":0.9990000128746033,"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":0.9990000128746033,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.998199999332428,"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":0.9977999925613403,"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/computer-science","display_name":"Computer science","score":0.7988603115081787},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6462552547454834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6053033471107483},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5865269899368286},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.551922082901001},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4970398247241974},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3718714714050293},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33577144145965576},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11142200231552124},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.08401301503181458},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06681853532791138}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7988603115081787},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6462552547454834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6053033471107483},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5865269899368286},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.551922082901001},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4970398247241974},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3718714714050293},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33577144145965576},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11142200231552124},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.08401301503181458},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06681853532791138},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680582","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2117539524","https://openalex.org/W2397830550","https://openalex.org/W2925148167","https://openalex.org/W2963182550","https://openalex.org/W2991216808","https://openalex.org/W3035750252","https://openalex.org/W3084053805","https://openalex.org/W3177015573","https://openalex.org/W3201726317","https://openalex.org/W3216568609","https://openalex.org/W4304092477","https://openalex.org/W4312401240","https://openalex.org/W4312818263","https://openalex.org/W4312894203","https://openalex.org/W4382240089","https://openalex.org/W4383108713","https://openalex.org/W4385801269","https://openalex.org/W4386065433","https://openalex.org/W4386071547","https://openalex.org/W4386071798","https://openalex.org/W4386075580","https://openalex.org/W4386076668","https://openalex.org/W4388191323","https://openalex.org/W4390874575","https://openalex.org/W4394625830"],"related_works":["https://openalex.org/W4394775207","https://openalex.org/W4389474468","https://openalex.org/W4300172004","https://openalex.org/W4321649381","https://openalex.org/W2997645659","https://openalex.org/W3180787869","https://openalex.org/W3203792196","https://openalex.org/W2955455867","https://openalex.org/W4295929828","https://openalex.org/W3156096827"],"abstract_inverted_index":{"Multi-modal":[0],"Unsupervised":[1],"Domain":[2],"Adaptation":[3],"(MM-UDA)":[4],"for":[5,173],"large-scale":[6],"3D":[7,14,115,179],"semantic":[8,116],"segmentation":[9],"involves":[10],"adapting":[11],"2D":[12,130,167],"and":[13,45,150,180],"models":[15],"to":[16,34,55,59,64,68,139,164],"a":[17,101],"target":[18,46],"domain":[19,37,112],"without":[20],"labels,":[21],"which":[22,106],"significantly":[23],"reduces":[24],"the":[25,36,43,60,80,134,141,161,177],"labor-intensive":[26],"annotations.":[27],"Existing":[28],"MM-UDA":[29],"methods":[30],"have":[31],"often":[32],"attempted":[33],"mitigate":[35,72],"discrepancy":[38],"by":[39],"aligning":[40],"features":[41,131],"between":[42,121,176],"source":[44],"data.":[47],"However,":[48],"this":[49,73,76],"implementation":[50],"falls":[51],"short":[52],"when":[53],"applied":[54],"image":[56],"perception":[57],"due":[58],"susceptibility":[61],"of":[62,82,143,147],"images":[63],"environmental":[65],"changes":[66],"compared":[67],"point":[69],"clouds.":[70],"To":[71,95],"limitation,":[74],"in":[75,114,160,198],"work,":[77],"we":[78,99],"explore":[79],"potentials":[81],"an":[83],"off-the-shelf":[84],"Contrastive":[85],"Language-Image":[86],"Pre-training":[87],"(CLIP)":[88],"model":[89],"with":[90],"rich":[91],"whilst":[92],"heterogeneous":[93],"knowledge.":[94],"make":[96],"CLIP":[97,109],"task-specific,":[98],"propose":[100],"top-performing":[102],"method,":[103],"dubbed":[104],"CLIP2UDA,":[105],"makes":[107],"frozen":[108],"reward":[110],"unsupervised":[111],"adaptation":[113,201],"segmentation.":[117],"Specifically,":[118],"CLIP2UDA":[119],"alternates":[120],"two":[122],"steps":[123],"during":[124],"adaptation:":[125],"(a)":[126],"Learning":[127,152],"task-specific":[128],"prompt.":[129],"response":[132],"from":[133],"visual":[135,168],"encoder":[136],"are":[137],"employed":[138],"initiate":[140],"learning":[142],"adaptive":[144],"text":[145],"prompt":[146],"each":[148],"domain,":[149],"(b)":[151],"multi-modal":[153],"domain-invariant":[154],"representations.":[155],"These":[156],"representations":[157],"interact":[158],"hierarchically":[159],"shared":[162],"decoder":[163],"obtain":[165],"unified":[166,181],"predictions.":[169],"This":[170],"enhancement":[171],"allows":[172],"effective":[174],"alignment":[175],"modality-specific":[178],"feature":[182],"space":[183],"via":[184],"cross-modal":[185],"mutual":[186],"learning.":[187],"Extensive":[188],"experimental":[189],"results":[190],"demonstrate":[191],"that":[192],"our":[193],"method":[194],"outperforms":[195],"state-of-the-art":[196],"competitors":[197],"several":[199],"widely-recognized":[200],"scenarios.":[202],"Code":[203],"is":[204],"available":[205],"at:":[206],"https://github.com/Barcaaaa/CLIP2UDA.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-02T14:50:37.381335","created_date":"2025-10-10T00:00:00"}