{"id":"https://openalex.org/W4403790998","doi":"https://doi.org/10.1145/3664647.3681401","title":"Adaptive Vision Transformer for Event-Based Human Pose Estimation","display_name":"Adaptive Vision Transformer for Event-Based Human Pose Estimation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403790998","doi":"https://doi.org/10.1145/3664647.3681401"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681401","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681401","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101159421","display_name":"Nannan Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nannan Yu","raw_affiliation_strings":["Dalian University of Technology, Dalian, Liaoning, China"],"raw_orcid":"https://orcid.org/0009-0008-1049-6317","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, Liaoning, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tao Ma","orcid":"https://orcid.org/0009-0005-1736-6863"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Ma","raw_affiliation_strings":["Dalian University of Technology, Dalian, Liaoning, China"],"raw_orcid":"https://orcid.org/0009-0005-1736-6863","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, Liaoning, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062571708","display_name":"Jiqing Zhang","orcid":"https://orcid.org/0000-0002-0061-5465"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiqing Zhang","raw_affiliation_strings":["Dalian Martime University, Dalian, Liaoning, China"],"raw_orcid":"https://orcid.org/0000-0002-0061-5465","affiliations":[{"raw_affiliation_string":"Dalian Martime University, Dalian, Liaoning, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101398194","display_name":"Yuji Zhang","orcid":"https://orcid.org/0000-0002-5402-7503"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuji Zhang","raw_affiliation_strings":["Dalian University of Technology, Dalian, Liaoning, China"],"raw_orcid":"https://orcid.org/0000-0002-5402-7503","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, Liaoning, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101287332","display_name":"Qirui Bao","orcid":"https://orcid.org/0009-0002-3790-3046"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qirui Bao","raw_affiliation_strings":["Dalian University of Technology, Dalian, Liaoning, China"],"raw_orcid":"https://orcid.org/0009-0002-3790-3046","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, Liaoning, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003257736","display_name":"Xiaopeng Wei","orcid":"https://orcid.org/0000-0002-8497-611X"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Wei","raw_affiliation_strings":["Dalian University of Technology, Dalian, Liaoning, China"],"raw_orcid":"https://orcid.org/0000-0002-8497-611X","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, Liaoning, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068792201","display_name":"Xin Yang","orcid":"https://orcid.org/0000-0002-8046-722X"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Yang","raw_affiliation_strings":["Dalian University of Technology, Dalian, Liaoning, China"],"raw_orcid":"https://orcid.org/0000-0002-8046-722X","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, Liaoning, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2833","last_page":"2841"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9993000030517578,"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":0.9993000030517578,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9969000220298767,"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/computer-science","display_name":"Computer science","score":0.6591039299964905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6120200753211975},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6095225811004639},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5773745775222778},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.5426637530326843},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13603076338768005},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08343428373336792},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06469964981079102}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6591039299964905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6120200753211975},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6095225811004639},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5773745775222778},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.5426637530326843},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13603076338768005},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08343428373336792},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06469964981079102}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681401","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681401","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1975697167","https://openalex.org/W2095614026","https://openalex.org/W2559085405","https://openalex.org/W2789435382","https://openalex.org/W2962954622","https://openalex.org/W2963127485","https://openalex.org/W2963402313","https://openalex.org/W2964221239","https://openalex.org/W2998654373","https://openalex.org/W3034399482","https://openalex.org/W3101118898","https://openalex.org/W3176892444","https://openalex.org/W3183654790","https://openalex.org/W3189897383","https://openalex.org/W3203771370","https://openalex.org/W3203925315","https://openalex.org/W4205982568","https://openalex.org/W4214493076","https://openalex.org/W4214508443","https://openalex.org/W4224992933","https://openalex.org/W4242177601","https://openalex.org/W4309160143","https://openalex.org/W4313046728","https://openalex.org/W4321512628","https://openalex.org/W4385453100","https://openalex.org/W4386075690","https://openalex.org/W4386075741","https://openalex.org/W4386253639","https://openalex.org/W4387675699","https://openalex.org/W4387986991","https://openalex.org/W4389883212"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Event-based":[0],"human":[1,76,164],"pose":[2,77,165],"estimation":[3,78,166,202],"has":[4],"gained":[5],"popularity":[6],"due":[7],"to":[8,40,116,143,187],"the":[9,42,56,94,100,122,125,132],"benefits":[10],"of":[11,27,58,96,124],"high":[12,16],"temporal":[13],"resolution":[14],"and":[15,37,88,207],"dynamic":[17,154],"range":[18],"offered":[19],"by":[20,120],"event":[21,28,80],"cameras.":[22,81],"The":[23,181,204],"inherent":[24],"spatial":[25],"sparsity":[26],"data":[29],"makes":[30],"discarding":[31],"less":[32,146],"significant":[33],"regions":[34],"a":[35,51,71,153,170],"straightforward":[36],"effective":[38],"way":[39],"decrease":[41],"computation.":[43],"However,":[44],"implementing":[45],"this":[46,63],"operation":[47],"in":[48,149,163,201],"CNNs":[49],"poses":[50],"challenge,":[52],"as":[53],"it":[54],"disrupts":[55],"regularity":[57],"dense":[59],"convolutional":[60],"workload.":[61],"In":[62],"paper,":[64],"we":[65,83,109,135,168],"propose":[66,137],"an":[67,111,138],"adaptive":[68,86,112,139],"vision":[69],"transformer,":[70],"novel":[72],"efficient":[73],"backbone":[74],"for":[75],"with":[79],"Specifically,":[82],"present":[84],"two":[85],"patch":[87,113],"token":[89,140,155],"sampling":[90,114],"approaches":[91],"based":[92],"on":[93],"characteristics":[95],"events,":[97],"thereby":[98],"reducing":[99],"computational":[101],"load":[102],"while":[103],"still":[104],"achieving":[105],"comparable":[106],"performance.":[107],"Firstly,":[108],"design":[110],"scheme":[115],"eliminate":[117],"inactivity":[118],"patches":[119],"assessing":[121],"entropy":[123],"events":[126],"before":[127],"they":[128],"are":[129,209],"inputted":[130],"into":[131],"transformer.":[133],"Secondly,":[134],"further":[136],"reduction":[141],"strategy":[142],"selectively":[144],"remove":[145],"informative":[147],"tokens":[148],"transformer":[150],"layers":[151],"through":[152],"pruning":[156],"algorithm.":[157],"To":[158],"exploit":[159],"event-based":[160],"visual":[161],"cues":[162],"tasks,":[167],"construct":[169],"large-scale":[171],"frame-event-based":[172],"dataset,":[173],"dubbed":[174],"Event":[175],"Multi":[176],"Movement":[177],"HPE":[178],"(EventMM":[179],"HPE).":[180],"dataset":[182,208],"provides":[183],"annotation":[184],"frequencies":[185],"up":[186],"240":[188],"Hz.":[189],"Extensive":[190],"experiments":[191],"demonstrate":[192],"that":[193],"our":[194],"proposed":[195],"approach":[196],"outperforms":[197],"existing":[198],"state-of-the-art":[199],"methods":[200],"accuracy.":[203],"source":[205],"code":[206],"available":[210],"at":[211],"https://github.com/doublemanyu/Adaptive-Vision-Transformer-for-Event-Based-HPE.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}