{"id":"https://openalex.org/W4414360067","doi":"https://doi.org/10.24963/ijcai.2025/88","title":"Egocentric Object-Interaction Anticipation with Retentive and Predictive Learning","display_name":"Egocentric Object-Interaction Anticipation with Retentive and Predictive Learning","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360067","doi":"https://doi.org/10.24963/ijcai.2025/88"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/88","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/88","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-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":"https://openalex.org/A5101103335","display_name":"Guo Chen","orcid":"https://orcid.org/0009-0009-0944-6651"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guo Chen","raw_affiliation_strings":["Nanjing University"],"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018560644","display_name":"Yifei Huang","orcid":"https://orcid.org/0000-0001-8067-6227"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yifei Huang","raw_affiliation_strings":["The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029627390","display_name":"Zheng Yang","orcid":"https://orcid.org/0000-0002-4620-4223"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin-dong Zheng","raw_affiliation_strings":["Nanjing University"],"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101706512","display_name":"Yicheng Liu","orcid":"https://orcid.org/0000-0003-0318-7870"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yicheng Liu","raw_affiliation_strings":["Nanjing University"],"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108891681","display_name":"Jiahao Wang","orcid":"https://orcid.org/0009-0000-5496-9720"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jiahao Wang","raw_affiliation_strings":["Kuaishou Technology"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100679289","display_name":"Tong Lu","orcid":"https://orcid.org/0000-0001-5805-5336"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Lu","raw_affiliation_strings":["Nanjing University"],"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101103335"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33771885,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"783","last_page":"791"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9071000218391418,"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"}},"topics":[{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9071000218391418,"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/anticipation","display_name":"Anticipation (artificial intelligence)","score":0.8356000185012817},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5325000286102295},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4113999903202057},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.35350000858306885},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.2971000075340271},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.2930000126361847}],"concepts":[{"id":"https://openalex.org/C176777502","wikidata":"https://www.wikidata.org/wiki/Q4774623","display_name":"Anticipation (artificial intelligence)","level":2,"score":0.8356000185012817},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5649999976158142},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5325000286102295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4957999885082245},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4113999903202057},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3806999921798706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3677999973297119},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3409000039100647},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C2778061373","wikidata":"https://www.wikidata.org/wiki/Q1315146","display_name":"Predictive coding","level":3,"score":0.2700999975204468},{"id":"https://openalex.org/C20685875","wikidata":"https://www.wikidata.org/wiki/Q7239678","display_name":"Predictive validity","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26330000162124634},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/88","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/88","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Egocentric":[0],"object-interaction":[1],"anticipation":[2,109],"is":[3],"critical":[4],"for":[5,69,74],"applications":[6],"like":[7],"augmented":[8],"reality":[9],"and":[10,22,41,46,56,78,114,137],"robotics,":[11],"but":[12],"existing":[13,123],"methods":[14],"struggle":[15],"with":[16],"misaligned":[17],"egocentric":[18],"encoding,":[19,71],"insufficient":[20],"supervision,":[21],"underutilized":[23],"historical":[24,93],"context.":[25],"These":[26],"limitations":[27],"stem":[28],"from":[29],"a":[30,53],"lack":[31],"of":[32,100,131],"focus":[33],"on":[34],"retention,":[35],"i.e.,":[36,43],"retaining":[37],"long-term":[38,88],"object-centric":[39],"interactions,":[40],"prediction,":[42],"future-centric":[44],"encoding":[45],"future":[47,75],"uncertainty":[48,76],"modeling.":[49],"We":[50,96],"introduce":[51],"EgoAnticipator,":[52],"novel":[54],"Retentive":[55],"Predictive":[57],"Learning":[58],"framework":[59,102,121],"that":[60,119],"addresses":[61],"these":[62],"challenges.":[63],"Our":[64],"approach":[65],"combines":[66],"retentive":[67,136],"pre-training":[68,73],"domain-specific":[70],"predictive":[72,138],"modeling,":[77],"mirror":[79],"distillation":[80],"to":[81,91],"transfer":[82],"future-informed":[83],"knowledge.":[84],"Additionally,":[85],"we":[86],"propose":[87],"memory":[89],"prompting":[90],"integrate":[92],"interaction":[94,108],"cues.":[95],"evaluate":[97],"the":[98,104,129],"effectiveness":[99,130],"our":[101,120,135],"using":[103],"Ego4D":[105],"short-term":[106],"object":[107],"benchmark,":[110],"covering":[111],"both":[112],"STAv1":[113],"STAv2.":[115],"Extensive":[116],"experiments":[117],"demonstrate":[118],"outperforms":[122],"methods,":[124],"while":[125],"ablation":[126],"studies":[127],"highlight":[128],"each":[132],"design":[133],"inside":[134],"learning":[139],"framework.":[140]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}