{"id":"https://openalex.org/W7143494263","doi":"https://doi.org/10.1111/cgf.70368","title":"Enhancing Robust Category\u2010Agnostic Pose Estimation through Multi\u2010Modal Feature Alignment","display_name":"Enhancing Robust Category\u2010Agnostic Pose Estimation through Multi\u2010Modal Feature Alignment","publication_year":2026,"publication_date":"2026-03-30","ids":{"openalex":"https://openalex.org/W7143494263","doi":"https://doi.org/10.1111/cgf.70368"},"language":"en","primary_location":{"id":"doi:10.1111/cgf.70368","is_oa":false,"landing_page_url":"https://doi.org/10.1111/cgf.70368","pdf_url":null,"source":{"id":"https://openalex.org/S67831204","display_name":"Computer Graphics Forum","issn_l":"0167-7055","issn":["0167-7055","1467-8659"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Graphics Forum","raw_type":"journal-article"},"type":"article","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":null,"display_name":"Boxuan Li","orcid":"https://orcid.org/0009-0004-6596-6989"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boxuan Li","raw_affiliation_strings":["Pen\u2010Tung Sah Institute of Micro\u2010Nano Science and Technology Xiamen University"],"raw_orcid":"https://orcid.org/0009-0004-6596-6989","affiliations":[{"raw_affiliation_string":"Pen\u2010Tung Sah Institute of Micro\u2010Nano Science and Technology Xiamen University","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"last","author":{"id":null,"display_name":"Juan Liu","orcid":"https://orcid.org/0000-0002-6210-4230"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Juan Liu","raw_affiliation_strings":["Pen\u2010Tung Sah Institute of Micro\u2010Nano Science and Technology Xiamen University"],"raw_orcid":"https://orcid.org/0000-0002-6210-4230","affiliations":[{"raw_affiliation_string":"Pen\u2010Tung Sah Institute of Micro\u2010Nano Science and Technology Xiamen University","institution_ids":["https://openalex.org/I75867142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75867142"],"apc_list":{"value":3710,"currency":"USD","value_usd":3710},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32081227,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7577000260353088,"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":0.7577000260353088,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.06949999928474426,"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":0.04690000042319298,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.6265000104904175},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6074000000953674},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5909000039100647},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4260999858379364},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.31189998984336853},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.2676999866962433}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.84170001745224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.775600016117096},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.6265000104904175},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6074000000953674},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5909000039100647},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5005000233650208},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4260999858379364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32109999656677246},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.257999986410141},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.2540999948978424},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1111/cgf.70368","is_oa":false,"landing_page_url":"https://doi.org/10.1111/cgf.70368","pdf_url":null,"source":{"id":"https://openalex.org/S67831204","display_name":"Computer Graphics Forum","issn_l":"0167-7055","issn":["0167-7055","1467-8659"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Graphics Forum","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6147603988647461}],"awards":[{"id":"https://openalex.org/G966997749","display_name":null,"funder_award_id":"3502Z202373023","funder_id":"https://openalex.org/F4320316884","funder_display_name":"Natural Science Foundation of Xiamen City"}],"funders":[{"id":"https://openalex.org/F4320316884","display_name":"Natural Science Foundation of Xiamen City","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2012885984","https://openalex.org/W2113325037","https://openalex.org/W2284800790","https://openalex.org/W2798336850","https://openalex.org/W2900273708","https://openalex.org/W2967819436","https://openalex.org/W3035263170","https://openalex.org/W3121137185","https://openalex.org/W3138516171","https://openalex.org/W3159481202","https://openalex.org/W4292787291","https://openalex.org/W4313036259","https://openalex.org/W4386076411"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Category\u2010Agnostic":[1],"Pose":[2],"Estimation":[3],"(CAPE)":[4],"aims":[5],"to":[6,68,77,108],"detect":[7],"keypoints":[8],"for":[9,27],"objects":[10],"of":[11,43,60,73],"any":[12],"category":[13],"using":[14,54],"only":[15],"a":[16,22,49,123,152],"few":[17],"labeled":[18],"samples,":[19],"making":[20],"it":[21],"challenging":[23,146],"yet":[24],"crucial":[25],"task":[26],"general\u2010purpose":[28],"visual":[29,36,55],"understanding.":[30],"Existing":[31],"methods":[32],"rely":[33],"on":[34,127],"either":[35],"or":[37],"textual":[38,65],"inputs,":[39],"but":[40],"the":[41,70,97,115,128,145,158],"lack":[42],"cross\u2010modal":[44,106],"interaction":[45],"limits":[46],"generalization.":[47],"Without":[48],"unified":[50],"input":[51],"representation,":[52],"solely":[53],"features":[56],"hinders":[57],"consistent":[58],"prediction":[59],"same\u2010type":[61,74],"keypoints,":[62,75],"while":[63,114],"fixed":[64],"representations":[66],"fail":[67],"capture":[69],"diverse":[71],"characteristics":[72],"leading":[76],"coarse":[78],"and":[79,99,110,142],"over\u2010generalized":[80],"outputs.":[81],"To":[82],"address":[83],"these":[84],"limitations,":[85],"we":[86],"propose":[87],"two":[88],"multi\u2010modal":[89],"frameworks":[90],"that":[91,133],"perform":[92],"visual\u2010textual":[93],"integration":[94],"at":[95],"both":[96,140],"feature":[98],"decision":[100],"levels.":[101],"Our":[102],"feature\u2010level":[103],"module":[104],"leverages":[105],"attention":[107],"align":[109],"enhance":[111],"keypoint":[112],"representations,":[113],"decision\u2010level":[116],"fusion":[117],"adaptively":[118],"combines":[119],"modality\u2010specific":[120],"predictions":[121],"through":[122],"modality\u2010consistency":[124],"loss.":[125],"Experiments":[126],"large\u2010scale":[129],"MP\u2010100":[130],"dataset":[131],"demonstrate":[132],"our":[134,149],"method":[135],"surpasses":[136],"existing":[137],"baselines":[138],"in":[139,155],"accuracy":[141],"robustness.":[143],"Under":[144],"1\u2010shot":[147],"setting,":[148],"model":[150],"achieves":[151],"0.58%":[153],"improvement":[154],"PCK0.2":[156],"over":[157],"state\u2010of\u2010the\u2010art":[159],"CAPE":[160],"method.":[161]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-31T00:00:00"}