{"id":"https://openalex.org/W4404402316","doi":"https://doi.org/10.1109/iccv51701.2025.02125","title":"CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models","display_name":"CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404402316","doi":"https://doi.org/10.1109/iccv51701.2025.02125"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02125","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.06869","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100659576","display_name":"Junho Kim","orcid":"https://orcid.org/0000-0003-2809-9244"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junho Kim","raw_affiliation_strings":["EverEx"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EverEx","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006604581","display_name":"Hyungjin Chung","orcid":"https://orcid.org/0000-0003-3202-0893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyungjin Chung","raw_affiliation_strings":["EverEx"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EverEx","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007457176","display_name":"Byung\u2010Hoon Kim","orcid":"https://orcid.org/0000-0001-8949-4833"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Byung-Hoon Kim","raw_affiliation_strings":["EverEx"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EverEx","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0006686,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22889","last_page":"22898"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9703999757766724,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9703999757766724,"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/T13629","display_name":"Text Readability and Simplification","score":0.9466000199317932,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6053452491760254},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5537447333335876},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.5032493472099304},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4881301820278168},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4631898105144501},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08581942319869995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6053452491760254},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5537447333335876},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.5032493472099304},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4881301820278168},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4631898105144501},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08581942319869995},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02125","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.06869","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.06869","pdf_url":"https://arxiv.org/pdf/2411.06869","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.06869","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.06869","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.06869","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.06869","pdf_url":"https://arxiv.org/pdf/2411.06869","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404402316.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4391695420","https://openalex.org/W2711238126","https://openalex.org/W4308083507","https://openalex.org/W2286009621","https://openalex.org/W2900273708","https://openalex.org/W3103544346","https://openalex.org/W4282941460","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Category-agnostic":[0],"pose":[1,220],"estimation":[2],"(CAPE)":[3],"has":[4],"traditionally":[5],"relied":[6],"on":[7,57,162,179,188,200],"support":[8,58],"images":[9],"with":[10],"annotated":[11],"keypoints,":[12],"a":[13,197,212],"process":[14,144],"that":[15,139],"is":[16,223],"often":[17,51],"cumbersome":[18],"and":[19,45,74,106,123,155,183,207],"may":[20],"fail":[21],"to":[22,62,113,131,169,173],"fully":[23,63],"capture":[24],"the":[25,36,65,75,90,129,142,171,180,201,205,216],"necessary":[26],"correspondences":[27],"across":[28,191],"diverse":[29],"object":[30],"categories.":[31],"Recent":[32],"efforts":[33],"have":[34],"explored":[35],"use":[37],"of":[38,218],"text":[39,108],"queries,":[40,59],"leveraging":[41],"their":[42,55,60,79,151],"enhanced":[43],"stability":[44],"generalization":[46],"capabilities.":[47],"However,":[48],"existing":[49],"approaches":[50],"remain":[52],"constrained":[53],"by":[54,78],"reliance":[56],"failure":[61],"utilize":[64],"rich":[66],"priors":[67],"embedded":[68],"in":[69,204,215],"pre-trained":[70],"large":[71,93],"language":[72,94],"models,":[73],"limitations":[76],"imposed":[77],"parametric":[80],"distribution":[81,154],"assumptions.":[82],"To":[83],"address":[84],"these":[85],"challenges,":[86],"we":[87,134],"introduce":[88],"CapeLLM,":[89],"first":[91],"multimodal":[92],"model":[95,181],"(MLLM)":[96],"designed":[97,125],"for":[98,127,145,158],"CAPE.":[99,132],"Our":[100,117,194],"method":[101,118],"only":[102,178],"employs":[103],"query":[104],"image":[105],"detailed":[107],"descriptions":[109],"as":[110],"an":[111,136],"input":[112,192],"estimate":[114],"category-agnostic":[115,219],"keypoints.":[116,147],"encompasses":[119],"effective":[120],"training":[121],"strategies":[122],"carefully":[124],"instructions":[126],"applying":[128],"MLLM":[130,172],"Moreover,":[133],"propose":[135],"inference":[137],"mechanism":[138],"further":[140],"enhances":[141],"reasoning":[143],"unseen":[146],"while":[148],"flexibly":[149],"modeling":[150],"underlying":[152],"spatial":[153],"uncertainty,":[156],"allowing":[157],"adaptive":[159],"refinement":[160],"based":[161],"contextual":[163],"cues.":[164],"We":[165],"conducted":[166],"extensive":[167],"experiments":[168],"apply":[170],"CAPE":[174],"effectively,":[175],"focusing":[176],"not":[177],"architecture":[182],"prompt":[184],"design":[185],"but":[186],"also":[187],"ensuring":[189],"robustness":[190],"variations.":[193],"approach":[195],"sets":[196],"new":[198],"state-of-the-art":[199],"MP-100":[202],"benchmark":[203],"1-shot":[206],"even":[208],"5-shot":[209],"setting,":[210],"marking":[211],"significant":[213],"advancement":[214],"field":[217],"estimation.":[221],"Code":[222],"available":[224],"at":[225],"https://github.com/Junhojuno/CapeLLM.":[226]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}