{"id":"https://openalex.org/W4409366649","doi":"https://doi.org/10.1609/aaai.v39i7.32800","title":"Collaborative Learning for 3D Hand-Object Reconstruction and Compositional Action Recognition from Egocentric RGB Videos Using Superquadrics","display_name":"Collaborative Learning for 3D Hand-Object Reconstruction and Compositional Action Recognition from Egocentric RGB Videos Using Superquadrics","publication_year":2025,"publication_date":"2025-04-11","ids":{"openalex":"https://openalex.org/W4409366649","doi":"https://doi.org/10.1609/aaai.v39i7.32800"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v39i7.32800","doi":"https://doi.org/10.1609/aaai.v39i7.32800","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i7.32800","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32800/34955","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,"listed_in":["jufo-2","norway-1"],"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"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32800/34955","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017172598","display_name":"Tze Ho Elden Tse","orcid":"https://orcid.org/0009-0000-5910-1509","observed_orcids":["https://orcid.org/0009-0000-5910-1509"]},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tze Ho Elden Tse","raw_affiliation_strings":["University of Birmingham"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Birmingham","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083780769","display_name":"Runyang Feng","orcid":"https://orcid.org/0000-0002-4912-6646","observed_orcids":["https://orcid.org/0000-0002-4912-6646"]},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runyang Feng","raw_affiliation_strings":["Jilin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jilin University","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071013046","display_name":"Linfang Zheng","orcid":"https://orcid.org/0009-0001-8006-8325","observed_orcids":["https://orcid.org/0009-0001-8006-8325"]},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Linfang Zheng","raw_affiliation_strings":["University of Birmingham"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Birmingham","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058108589","display_name":"Jiho Park","orcid":"https://orcid.org/0000-0002-1048-3881","observed_orcids":["https://orcid.org/0000-0002-1048-3881"]},"institutions":[{"id":"https://openalex.org/I205490536","display_name":"Dongguk University","ror":"https://ror.org/057q6n778","country_code":"KR","type":"education","lineage":["https://openalex.org/I205490536"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiho Park","raw_affiliation_strings":["Dongguk University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dongguk University","institution_ids":["https://openalex.org/I205490536"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yixing Gao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixing Gao","raw_affiliation_strings":["Jilin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jilin University","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080664764","display_name":"Jihie Kim","orcid":"https://orcid.org/0000-0003-2358-4021","observed_orcids":["https://orcid.org/0000-0003-2358-4021"]},"institutions":[{"id":"https://openalex.org/I205490536","display_name":"Dongguk University","ror":"https://ror.org/057q6n778","country_code":"KR","type":"education","lineage":["https://openalex.org/I205490536"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jihie Kim","raw_affiliation_strings":["Dongguk University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dongguk University","institution_ids":["https://openalex.org/I205490536"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085971943","display_name":"Ale\u0161 Leonardis","orcid":"https://orcid.org/0000-0003-0773-3277","observed_orcids":["https://orcid.org/0000-0003-0773-3277"]},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ales Leonardis","raw_affiliation_strings":["University of Birmingham"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Birmingham","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004895698","display_name":"Hyung Jin Chang","orcid":"https://orcid.org/0000-0001-7495-9677","observed_orcids":["https://orcid.org/0000-0001-7495-9677"]},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hyung Jin Chang","raw_affiliation_strings":["University of Birmingham"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Birmingham","institution_ids":["https://openalex.org/I79619799"]}]}],"institutions":[],"countries_distinct_count":3,"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":0.05329309,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":"7","first_page":"7437","last_page":"7445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.8223000168800354,"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":0.8223000168800354,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.12700000405311584,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.039900001138448715,"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/hand-object-interaction","display_name":"hand-object interaction","score":0.5989999771118164},{"id":"https://openalex.org/keywords/3d-hand-pose-estimation","display_name":"3D hand pose estimation","score":0.7799999713897705},{"id":"https://openalex.org/keywords/object-reconstruction","display_name":"object reconstruction","score":0.5550000071525574},{"id":"https://openalex.org/keywords/superquadrics","display_name":"superquadrics","score":0.8180000185966492},{"id":"https://openalex.org/keywords/egocentric-video","display_name":"egocentric video","score":0.8119999766349792},{"id":"https://openalex.org/keywords/collaborative-learning","display_name":"cooperative learning","score":0.6449999809265137},{"id":"https://openalex.org/keywords/unseen-objects","display_name":"unseen objects","score":0.7319999933242798}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7007168531417847},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.613186776638031},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.560310423374176},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5232918858528137},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5185861587524414},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5043100118637085},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4596199095249176},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37404441833496094},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0717521607875824},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v39i7.32800","doi":"https://doi.org/10.1609/aaai.v39i7.32800","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i7.32800","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32800/34955","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,"listed_in":["jufo-2","norway-1"],"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"}],"best_oa_location":{"id":"doi:10.1609/aaai.v39i7.32800","doi":"https://doi.org/10.1609/aaai.v39i7.32800","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i7.32800","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32800/34955","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,"listed_in":["jufo-2","norway-1"],"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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2909624354","display_name":null,"funder_award_id":"IITP\u20102024\u20102020\u20100\u201001789","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G6713437128","display_name":null,"funder_award_id":"62203184","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409366649.pdf","grobid_xml":"https://content.openalex.org/works/W4409366649.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W2619947201","https://openalex.org/W2805516822","https://openalex.org/W3107646798","https://openalex.org/W4394671432"],"related_works":["https://openalex.org/W7080142389","https://openalex.org/W2940216740","https://openalex.org/W4403081605","https://openalex.org/W4391877736","https://openalex.org/W7115326156","https://openalex.org/W2995473600","https://openalex.org/W2605973302","https://openalex.org/W4407253823","https://openalex.org/W4408272058","https://openalex.org/W2085158606"],"abstract_inverted_index":{"With":[0],"the":[1,38,51,106,109,121,132,143,167,173,187],"availability":[2],"of":[3,123,135],"egocentric":[4],"3D":[5,47,77,113],"hand-object":[6,18],"interaction":[7],"datasets,":[8],"there":[9],"is":[10],"increasing":[11],"interest":[12],"in":[13,40,189],"developing":[14],"unified":[15,107],"models":[16],"for":[17],"pose":[19],"estimation":[20],"and":[21,44,83,92,137,149,155,172,179],"action":[22,93,191],"recognition.":[23,192],"However,":[24],"existing":[25],"methods":[26,103],"still":[27],"struggle":[28],"to":[29,37,62,71,80],"recognise":[30],"seen":[31],"actions":[32,124],"on":[33,53,87],"unseen":[34,63],"objects":[35],"due":[36],"limitations":[39],"representing":[41],"object":[42,54,78,90],"shape":[43],"movement":[45],"using":[46],"bounding":[48,81],"boxes.":[49],"Additionally,":[50],"reliance":[52],"templates":[55],"at":[56],"test":[57],"time":[58],"limits":[59],"their":[60,85],"generalisability":[61],"objects.":[64],"To":[65],"address":[66],"these":[67],"challenges,":[68],"we":[69,98,119,182],"propose":[70],"leverage":[72],"superquadrics":[73],"as":[74,97],"an":[75],"alternative":[76],"representation":[79],"boxes":[82],"demonstrate":[84,183],"effectiveness":[86],"both":[88],"template-free":[89],"reconstruction":[91],"recognition":[94],"tasks.":[95],"Moreover,":[96],"find":[99],"that":[100,162],"pure":[101],"appearance-based":[102],"can":[104,163],"outperform":[105],"methods,":[108],"potential":[110],"benefits":[111],"from":[112],"geometric":[114,168],"information":[115],"remain":[116],"unclear.":[117],"Therefore,":[118],"study":[120],"compositionality":[122],"by":[125],"considering":[126],"a":[127,157],"more":[128],"challenging":[129],"task":[130],"where":[131],"training":[133],"combinations":[134],"verbs":[136],"nouns":[138],"do":[139],"not":[140],"overlap":[141],"with":[142,152],"testing":[144],"split.":[145],"We":[146],"extend":[147],"H2O":[148],"FPHA":[150],"datasets":[151],"compositional":[153],"splits":[154],"design":[156],"novel":[158],"collaborative":[159],"learning":[160],"framework":[161],"explicitly":[164],"reason":[165],"about":[166],"relations":[169],"between":[170],"hands":[171],"manipulated":[174],"object.":[175],"Through":[176],"extensive":[177],"quantitative":[178],"qualitative":[180],"evaluations,":[181],"significant":[184],"improvements":[185],"over":[186],"state-of-the-arts":[188],"(compositional)":[190]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-04-12T00:00:00"}