{"id":"https://openalex.org/W7138250129","doi":"https://doi.org/10.1609/aaai.v40i8.37546","title":"CLIP2Pose: Frozen CLIP as Semantic Guide for Domain Adaptive Pose Estimation","display_name":"CLIP2Pose: Frozen CLIP as Semantic Guide for Domain Adaptive Pose Estimation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138250129","doi":"https://doi.org/10.1609/aaai.v40i8.37546"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i8.37546","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37546","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i8.37546","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129665212","display_name":"Jiawen Li","orcid":null},"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":"Jiawen Li","raw_affiliation_strings":["East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129681044","display_name":"Fei Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107284","display_name":"Chongqing Academy of Science and Technology","ror":"https://ror.org/01gnzp994","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210107284"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Jiang","raw_affiliation_strings":["Chongqing academy of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing academy of Science and Technology","institution_ids":["https://openalex.org/I4210107284"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129739445","display_name":"Dandan Zhu","orcid":null},"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":"Dandan Zhu","raw_affiliation_strings":["East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113409492","display_name":"Jinxin Shi","orcid":null},"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":"Jinxin Shi","raw_affiliation_strings":["East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129709526","display_name":"Aimin Zhou","orcid":null},"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":"Aimin Zhou","raw_affiliation_strings":["East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.26226994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"8","first_page":"6208","last_page":"6216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.4966999888420105,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.4966999888420105,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.3490999937057495,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.031599998474121094,"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/robustness","display_name":"Robustness (evolution)","score":0.5898000001907349},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5814999938011169},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5587000250816345},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.5534999966621399},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4514000117778778},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.39149999618530273},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.37279999256134033},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.33059999346733093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8240000009536743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7297000288963318},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5898000001907349},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5814999938011169},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5587000250816345},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.5534999966621399},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5346999764442444},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.3125},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28200000524520874},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2718999981880188},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26269999146461487}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i8.37546","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37546","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"},{"id":"pmh:oai:ojs.aaai.org:article/37546","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i8.37546","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37546","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Unsupervised":[0],"domain":[1,146,168],"adaptive":[2,169],"pose":[3,28,174],"estimation":[4],"is":[5],"a":[6,66,85,118,150],"fundamental":[7],"yet":[8],"challenging":[9],"task":[10],"due":[11],"to":[12,15,21,78,106],"the":[13,26,44,71,99,104,143],"need":[14],"transfer":[16],"from":[17],"labeled":[18],"synthetic":[19],"data":[20],"unlabeled":[22],"real":[23],"data.":[24],"Nevertheless,":[25],"underlying":[27],"semantics,":[29],"which":[30,49],"are":[31],"governed":[32],"by":[33,61,127],"spatial":[34],"structure,":[35],"remain":[36],"largely":[37],"consistent":[38,156],"across":[39,159],"domains.":[40],"This":[41,102],"observation":[42],"motivates":[43],"use":[45],"of":[46,74],"vision-language":[47],"models,":[48],"provide":[50],"domain-invariant":[51],"representations":[52],"that":[53,69,89,122,154,177],"align":[54],"well":[55],"with":[56],"high-level":[57],"semantic":[58,72,119],"concepts.":[59],"Motivated":[60],"this,":[62],"we":[63,116,148],"propose":[64,117],"CLIP2Pose,":[65],"novel":[67],"framework":[68],"leverages":[70],"robustness":[73],"frozen":[75],"CLIP":[76],"encoders":[77],"facilitate":[79],"cross-domain":[80],"generalization.":[81],"We":[82],"first":[83],"introduce":[84],"semantic-driven":[86],"prompt":[87],"mechanism":[88],"encodes":[90],"structural":[91,157],"priors,":[92],"domain-specific":[93],"appearance,":[94],"and":[95,111,137,145,162,172],"instance-level":[96],"context":[97],"into":[98],"image":[100],"representation.":[101],"guides":[103],"model":[105],"focus":[107],"on":[108,130,167],"semantically":[109],"meaningful":[110],"structurally":[112],"relevant":[113],"features.":[114],"Next,":[115],"modulation":[120],"module":[121],"adaptively":[123],"refines":[124],"visual":[125,138],"features":[126],"conditioning":[128],"them":[129],"prompt-derived":[131],"embeddings,":[132],"enhancing":[133],"alignment":[134,152],"between":[135],"semantics":[136],"patterns.":[139],"To":[140],"further":[141],"bridge":[142],"modality":[144],"gaps,":[147],"design":[149],"directional":[151],"loss":[153],"encourages":[155],"reasoning":[158],"both":[160],"vision":[161],"language":[163],"representations.":[164],"Extensive":[165],"experiments":[166],"human":[170],"body":[171],"hand":[173],"benchmarks":[175],"show":[176],"CLIP2Pose":[178],"achieves":[179],"state-of-the-art":[180],"performance.":[181]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}