{"id":"https://openalex.org/W7137892390","doi":"https://doi.org/10.1609/aaai.v40i21.38797","title":"Intention-Guided Cognitive Reasoning for Egocentric Long-Term Action Anticipation","display_name":"Intention-Guided Cognitive Reasoning for Egocentric Long-Term Action Anticipation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137892390","doi":"https://doi.org/10.1609/aaai.v40i21.38797"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i21.38797","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i21.38797","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i21.38797","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Qiaohui Chu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Qiaohui Chu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129641628","display_name":"Haoyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoyu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129683271","display_name":"Meng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110296061","display_name":"Yisen Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yisen Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129679718","display_name":"Haoxiang Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoxiang Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129684253","display_name":"Liqiang Nie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.8349,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.94492132,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"40","issue":"21","first_page":"17436","last_page":"17444"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.5317999720573425,"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":0.5317999720573425,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.23280000686645508,"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/T11431","display_name":"Action Observation and Synchronization","score":0.06769999861717224,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/anticipation","display_name":"Anticipation (artificial intelligence)","score":0.7896000146865845},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.7448999881744385},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6431000232696533},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.5782999992370605},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.570900022983551},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5504999756813049},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4388999938964844},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.412200003862381}],"concepts":[{"id":"https://openalex.org/C176777502","wikidata":"https://www.wikidata.org/wiki/Q4774623","display_name":"Anticipation (artificial intelligence)","level":2,"score":0.7896000146865845},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7448999881744385},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6431000232696533},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.5782999992370605},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.570900022983551},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.5544999837875366},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5504999756813049},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5142999887466431},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4388999938964844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4293000102043152},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.41449999809265137},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3828999996185303},{"id":"https://openalex.org/C2776289891","wikidata":"https://www.wikidata.org/wiki/Q1931511","display_name":"Neglect","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.3653999865055084},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.36010000109672546},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3562999963760376},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3531999886035919},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i21.38797","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i21.38797","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"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i21.38797","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i21.38797","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":{"Long-term":[0],"action":[1,79,98,132],"anticipation":[2,133],"from":[3,31,41,92],"egocentric":[4,78],"video":[5],"is":[6],"critical":[7],"for":[8,77],"applications":[9],"such":[10],"as":[11],"human-computer":[12],"interaction":[13,94],"and":[14,23,51,53,62,96,140,153],"assistive":[15],"technologies,":[16],"where":[17],"anticipating":[18],"user":[19],"intent":[20],"enables":[21],"proactive":[22],"context-aware":[24],"AI":[25],"assistance.":[26],"However,":[27],"existing":[28],"approaches":[29],"suffer":[30],"three":[32],"key":[33],"limitations:":[34],"1)":[35],"underutilization":[36],"of":[37,46,56],"fine-grained":[38],"visual":[39,124],"cues":[40],"hand-object":[42,93],"interactions,":[43],"2)":[44],"neglect":[45],"semantic":[47],"dependencies":[48],"between":[49],"verbs":[50],"nouns,":[52],"3)":[54],"lack":[55],"explicit":[57,117],"cognitive":[58,118],"reasoning,":[59],"limiting":[60],"generalization":[61,155],"long-term":[63],"forecasting":[64],"ability.":[65],"To":[66],"overcome":[67],"these":[68],"challenges,":[69],"we":[70],"propose":[71],"INSIGHT,":[72],"a":[73,101,111,121],"unified":[74],"two-stage":[75],"framework":[76],"anticipation.":[80],"In":[81,105],"the":[82,106],"first":[83],"stage,":[84,108],"INSIGHT":[85,146],"focuses":[86],"on":[87,137],"extracting":[88],"semantically":[89],"rich":[90],"features":[91],"regions":[95],"enhances":[97],"representations":[99],"using":[100],"verb-noun":[102],"co-occurrence":[103],"matrix.":[104],"second":[107],"it":[109],"introduces":[110],"reinforcement":[112],"learning-based":[113],"module":[114],"that":[115,145],"simulates":[116],"reasoning":[119],"through":[120],"structured":[122],"process:":[123],"perception":[125],"(think)":[126],"\u2192":[127,131],"intention":[128],"inference":[129],"(reason)":[130],"(answer).":[134],"Extensive":[135],"experiments":[136],"Ego4D,":[138],"EPIC-Kitchens-55,":[139],"EGTEA":[141],"Gaze+":[142],"benchmarks":[143],"show":[144],"achieves":[147],"state-of-the-art":[148],"performance,":[149],"demonstrating":[150],"its":[151],"effectiveness":[152],"strong":[154],"capability.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-18T00:00:00"}
