{"id":"https://openalex.org/W7137958727","doi":"https://doi.org/10.1609/aaai.v40i15.38244","title":"Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding","display_name":"Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137958727","doi":"https://doi.org/10.1609/aaai.v40i15.38244"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i15.38244","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38244","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.v40i15.38244","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129641628","display_name":"Haoyu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoyu Zhang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen)\nPengcheng Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen)\nPengcheng Laboratory","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qiaohui Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiaohui Chu","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen)\nPengcheng Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen)\nPengcheng Laboratory","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129683271","display_name":"Meng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I44445938","display_name":"Shandong Jianzhu University","ror":"https://ror.org/01gbfax37","country_code":"CN","type":"education","lineage":["https://openalex.org/I44445938"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Liu","raw_affiliation_strings":["Shandong Jianzhu University\nZhongguancun Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong Jianzhu University\nZhongguancun Academy","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129679718","display_name":"Haoxiang Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoxiang Shi","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen)\nPengcheng Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen)\nPengcheng Laboratory","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129683426","display_name":"Yaowei Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaowei Wang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen)\nPengcheng Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen)\nPengcheng Laboratory","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129684253","display_name":"Liqiang Nie","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5129641628"],"corresponding_institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210136793"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19241774,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"15","first_page":"12502","last_page":"12510"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9118000268936157,"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":0.9118000268936157,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.016200000420212746,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.013500000350177288,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/endocentric-and-exocentric","display_name":"Endocentric and exocentric","score":0.8718000054359436},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.6403999924659729},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5932000279426575},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.578000009059906},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.32749998569488525},{"id":"https://openalex.org/keywords/knowledge-acquisition","display_name":"Knowledge acquisition","score":0.3109999895095825}],"concepts":[{"id":"https://openalex.org/C131042201","wikidata":"https://www.wikidata.org/wiki/Q493198","display_name":"Endocentric and exocentric","level":4,"score":0.8718000054359436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7491000294685364},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.6403999924659729},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5932000279426575},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.578000009059906},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.49459999799728394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46700000762939453},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i15.38244","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38244","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.v40i15.38244","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38244","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":[{"score":0.7500715255737305,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"AI":[0],"personal":[1],"assistants,":[2],"deployed":[3],"through":[4],"robots":[5],"or":[6],"wearables,":[7],"require":[8],"embodied":[9],"understanding":[10],"to":[11,69,104],"collaborate":[12],"effectively":[13],"with":[14,93,127],"humans.":[15],"However,":[16],"current":[17],"Multimodal":[18],"Large":[19],"Language":[20],"Models":[21],"(MLLMs)":[22],"primarily":[23],"focus":[24],"on":[25],"third-person":[26],"(exocentric)":[27],"vision,":[28],"overlooking":[29],"the":[30,54,62,94,106,112],"unique":[31],"challenges":[32],"of":[33],"first-person":[34],"(egocentric)":[35],"videos.":[36],"Additionally,":[37],"high":[38],"acquisition":[39],"costs":[40],"limit":[41],"data":[42],"size,":[43],"impairing":[44],"MLLM":[45],"performance.":[46],"To":[47,74],"address":[48],"these":[49,158],"challenges,":[50],"we":[51,77,114],"propose":[52,115],"learning":[53,125],"mapping":[55,124],"between":[56],"exocentric":[57,64],"and":[58,119,134],"egocentric":[59,71,141,150],"domains,":[60],"leveraging":[61],"extensive":[63],"knowledge":[65],"within":[66],"existing":[67,145],"MLLMs":[68,146],"enhance":[70,105],"video":[72,151],"understanding.":[73],"this":[75],"end,":[76],"introduce":[78],"Ego-ExoClip,":[79],"a":[80,116,122],"pre-training":[81],"dataset":[82,96],"comprising":[83],"1.1M":[84],"synchronized":[85],"ego-exo":[86],"clip-text":[87],"pairs":[88],"derived":[89],"from":[90,101],"Ego-Exo4D,":[91],"together":[92],"instruction-tuning":[95],"EgoIT,":[97],"which":[98],"is":[99],"collected":[100],"multiple":[102],"sources":[103],"model's":[107],"instruction-following":[108],"capabilities.":[109],"Building":[110],"upon":[111],"datasets,":[113],"migration":[117],"strategy":[118],"further":[120],"design":[121],"progressive":[123],"pipeline":[126],"three":[128],"stages:":[129],"Demonstrator":[130],"Self-Preparation,":[131],"Demonstrator-Learner":[132],"Guidance,":[133],"Learner":[135],"Self-Practice.":[136],"Extensive":[137],"experiments":[138],"across":[139],"diverse":[140],"tasks":[142],"reveal":[143],"that":[144],"perform":[147],"inadequately":[148],"in":[149],"understanding,":[152],"while":[153],"our":[154],"model":[155],"significantly":[156],"outperforms":[157],"leading":[159],"models.":[160]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-18T00:00:00"}