{"id":"https://openalex.org/W4415708311","doi":"https://doi.org/10.1109/icme59968.2025.11209479","title":"MAPLE: Modality-Agnostic Prototype Learning for Egocentric Action Recognition","display_name":"MAPLE: Modality-Agnostic Prototype Learning for Egocentric Action Recognition","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708311","doi":"https://doi.org/10.1109/icme59968.2025.11209479"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5103366660","display_name":"Da Li","orcid":"https://orcid.org/0009-0001-1300-4129"},"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":"Da Li","raw_affiliation_strings":["Shandong Jianzhu University,Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong Jianzhu University,Jinan,China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111047389","display_name":"Di Zhou","orcid":"https://orcid.org/0000-0002-9248-7703"},"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":"Di Zhou","raw_affiliation_strings":["Shandong Jianzhu University,Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong Jianzhu University,Jinan,China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044881779","display_name":"Yishan Zou","orcid":"https://orcid.org/0009-0006-8450-0388"},"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":"Yishan Zou","raw_affiliation_strings":["Shandong Jianzhu University,Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong Jianzhu University,Jinan,China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080935093","display_name":"Shenghua Li","orcid":"https://orcid.org/0000-0002-9144-2167"},"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":"Shenghua Li","raw_affiliation_strings":["Shandong Jianzhu University,Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong Jianzhu University,Jinan,China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100457438","display_name":"Meng Liu","orcid":"https://orcid.org/0000-0002-1582-5764"},"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,Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong Jianzhu University,Jinan,China","institution_ids":["https://openalex.org/I44445938"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27152998,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9656000137329102,"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":0.9656000137329102,"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":0.005499999970197678,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.00279999990016222,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.673799991607666},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6011000275611877},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5952000021934509},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5604000091552734},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.511900007724762},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.505299985408783},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4652000069618225},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45809999108314514},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4296000003814697}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.736299991607666},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.673799991607666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.670799970626831},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6011000275611877},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5952000021934509},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5604000091552734},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.511900007724762},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.505299985408783},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4652000069618225},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45809999108314514},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.41990000009536743},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41269999742507935},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4106000065803528},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39410001039505005},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.30390000343322754},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29420000314712524},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C189645446","wikidata":"https://www.wikidata.org/wiki/Q350865","display_name":"Mirroring","level":2,"score":0.2632000148296356}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1995875735","https://openalex.org/W2162762857","https://openalex.org/W2593116425","https://openalex.org/W2798354744","https://openalex.org/W2897298014","https://openalex.org/W2897628926","https://openalex.org/W2963524571","https://openalex.org/W2964080999","https://openalex.org/W2964184826","https://openalex.org/W2971680695","https://openalex.org/W3035524453","https://openalex.org/W3118648637","https://openalex.org/W3170972077","https://openalex.org/W3196974791","https://openalex.org/W3205786327","https://openalex.org/W3213003795","https://openalex.org/W4312372834","https://openalex.org/W4312504063","https://openalex.org/W4372260217","https://openalex.org/W4386075869","https://openalex.org/W4402904188","https://openalex.org/W4403511263","https://openalex.org/W4404587457"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,79],"paper,":[2],"we":[3,81],"address":[4,78],"the":[5,40,70,123,134,151],"novel":[6],"task":[7],"of":[8,153],"egocentric":[9,25,154],"modality":[10],"generalization":[11,35],"action":[12,26,75,155],"recognition,":[13],"which":[14],"aims":[15],"to":[16,60,95,118],"learn":[17],"a":[18,87,91,104,110,147],"unified":[19],"discrete":[20],"representation":[21],"from":[22],"paired":[23],"multimodal":[24],"data":[27],"during":[28,43],"pre-training.":[29],"This":[30,99],"approach":[31],"enables":[32],"cross-modal":[33,129],"zero-shot":[34],"in":[36,122,150],"downstream":[37],"tasks,":[38],"where":[39],"modalities":[41],"available":[42],"inference":[44],"and":[45,109,126,136],"training":[46],"are":[47],"disjoint.":[48],"While":[49],"recent":[50],"efforts":[51],"have":[52,68],"focused":[53],"on":[54,133],"aligning":[55],"instance-level":[56],"or":[57],"temporal":[58],"features":[59],"reduce":[61],"feature":[62],"distribution":[63],"discrepancies":[64],"across":[65],"modalities,":[66],"they":[67],"overlooked":[69],"inherent":[71],"structural":[72],"categorization":[73],"within":[74],"data.":[76],"To":[77],"limitation,":[80],"propose":[82],"Modal-Agnostic":[83],"Prototype":[84],"Learning":[85],"(MAPLE),":[86],"framework":[88],"that":[89,140],"leverages":[90],"prototype":[92],"memory":[93],"bank":[94],"capture":[96],"categorical":[97],"structures.":[98],"is":[100],"further":[101],"enhanced":[102],"by":[103],"robust":[105,128],"semantic":[106],"disentanglement":[107],"module":[108],"moment":[111],"aggregation":[112],"mechanism,":[113],"enabling":[114],"semantically":[115],"similar":[116],"behaviors":[117],"cluster":[119],"more":[120],"closely":[121],"latent":[124],"space":[125],"promoting":[127],"generalization.":[130],"Extensive":[131],"experiments":[132],"Ego4D":[135],"WEAR":[137],"datasets":[138],"demonstrate":[139],"MAPLE":[141],"significantly":[142],"outperforms":[143],"existing":[144],"approaches,":[145],"marking":[146],"substantial":[148],"advancement":[149],"field":[152],"recognition.":[156]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-30T00:00:00"}