{"id":"https://openalex.org/W4408353521","doi":"https://doi.org/10.1109/icassp49660.2025.10888760","title":"Event Masked Autoencoder: Point-wise Action Recognition with Event-Based Cameras","display_name":"Event Masked Autoencoder: Point-wise Action Recognition with Event-Based Cameras","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353521","doi":"https://doi.org/10.1109/icassp49660.2025.10888760"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5049574394","display_name":"Jingkai Sun","orcid":"https://orcid.org/0000-0002-1032-2957"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jingkai Sun","raw_affiliation_strings":["Hong Kong University of Science and Technology,Guangzhou"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Guangzhou","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381904","display_name":"Qiang Zhang","orcid":"https://orcid.org/0000-0002-2828-9905"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiang Zhang","raw_affiliation_strings":["Hong Kong University of Science and Technology,Guangzhou"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Guangzhou","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101468620","display_name":"Jiaxu Wang","orcid":"https://orcid.org/0000-0003-1277-6896"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaxu Wang","raw_affiliation_strings":["Hong Kong University of Science and Technology,Guangzhou"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Guangzhou","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015422529","display_name":"Jiahang Cao","orcid":"https://orcid.org/0000-0003-4338-4414"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiahang Cao","raw_affiliation_strings":["Hong Kong University of Science and Technology,Guangzhou"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Guangzhou","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089850879","display_name":"Hao Cheng","orcid":"https://orcid.org/0000-0003-0534-4665"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Cheng","raw_affiliation_strings":["Hong Kong University of Science and Technology,Guangzhou"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Guangzhou","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100616654","display_name":"Renjing Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Renjing Xu","raw_affiliation_strings":["Hong Kong University of Science and Technology,Guangzhou"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Guangzhou","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5049574394"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6209,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88275879,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9973999857902527,"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":0.9973999857902527,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9972000122070312,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9746999740600586,"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/autoencoder","display_name":"Autoencoder","score":0.806358277797699},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7011824250221252},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6802547574043274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6102017164230347},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5631142854690552},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5192877650260925},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47705259919166565},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.43122440576553345},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40293094515800476},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.15322420001029968},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13348853588104248},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07301011681556702}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.806358277797699},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7011824250221252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6802547574043274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6102017164230347},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5631142854690552},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5192877650260925},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47705259919166565},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.43122440576553345},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40293094515800476},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.15322420001029968},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13348853588104248},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07301011681556702},{"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/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":24,"referenced_works":["https://openalex.org/W2745933219","https://openalex.org/W2810685774","https://openalex.org/W2922107638","https://openalex.org/W2966174534","https://openalex.org/W2987260487","https://openalex.org/W3025773901","https://openalex.org/W3040838455","https://openalex.org/W3109192943","https://openalex.org/W3128431487","https://openalex.org/W3134123147","https://openalex.org/W3138516171","https://openalex.org/W3163388905","https://openalex.org/W3186059296","https://openalex.org/W3189897383","https://openalex.org/W4292787316","https://openalex.org/W4312270234","https://openalex.org/W4312788538","https://openalex.org/W4313003697","https://openalex.org/W4385453100","https://openalex.org/W4405786332","https://openalex.org/W4408353317","https://openalex.org/W6687484953","https://openalex.org/W6755207826","https://openalex.org/W6763422710"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W2159052453","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W2803255133","https://openalex.org/W4297051394","https://openalex.org/W1576128429","https://openalex.org/W59693972","https://openalex.org/W2269464716"],"abstract_inverted_index":{"Dynamic":[0],"vision":[1,43],"sensors":[2],"(DVS)":[3],"are":[4],"bio-inspired":[5],"devices":[6],"that":[7,36,84,111,139],"capture":[8],"visual":[9],"information":[10,58],"in":[11,20],"the":[12,88,153,162,170,180],"form":[13],"of":[14,91,100,118,157,164],"asynchronous":[15],"events,":[16],"which":[17],"encode":[18],"changes":[19],"pixel":[21],"intensity":[22],"with":[23],"high":[24],"temporal":[25,57],"resolution":[26],"and":[27,66,86,115,146,155,183],"low":[28],"latency.":[29],"These":[30],"events":[31],"provide":[32],"rich":[33],"motion":[34],"cues":[35],"can":[37],"be":[38],"exploited":[39],"for":[40,94,179],"various":[41],"computer":[42],"tasks,":[44],"such":[45],"as":[46],"action":[47,53,95],"recognition.":[48,96],"However,":[49],"most":[50],"existing":[51],"DVS-based":[52],"recognition":[54],"methods":[55],"lose":[56],"during":[59],"data":[60,93,143,148,178],"transformation":[61],"or":[62,72],"suffer":[63],"from":[64,124],"noise":[65],"outliers":[67],"caused":[68],"by":[69,121],"sensor":[70],"imperfections":[71],"environmental":[73],"factors.":[74],"To":[75,161],"address":[76],"these":[77],"challenges,":[78],"we":[79,184],"propose":[80,185],"a":[81,105,113,186],"novel":[82,187],"framework":[83,98],"preserves":[85],"exploits":[87],"spatiotemporal":[89],"structure":[90],"event":[92,107,119,127,134,142,158,174,188,197],"Our":[97],"consists":[99],"two":[101],"main":[102],"components:":[103],"1)":[104],"point-wise":[106,147],"masked":[108,125],"autoencoder":[109],"(MAE)":[110],"learns":[112],"compact":[114],"discriminative":[116],"representation":[117],"patches":[120],"reconstructing":[122],"them":[123],"raw":[126,176],"camera":[128,175],"points":[129,135,159,177,189],"data;":[130],"2)":[131],"an":[132,141],"improved":[133],"patch":[136,190],"generation":[137],"algorithm":[138],"leverages":[140],"inlier":[144],"model":[145],"augmentation":[149],"techniques":[150],"to":[151,192],"enhance":[152],"quality":[154],"diversity":[156],"patches.":[160],"best":[163],"our":[165,167],"knowledge,":[166],"approach":[168],"introduces":[169],"pre-train":[171],"method":[172],"into":[173],"first":[181],"time,":[182],"embedding":[191],"utilize":[193],"transformer-based":[194],"models":[195],"on":[196],"cameras.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-02-26T08:16:20.718346","created_date":"2025-10-10T00:00:00"}