{"id":"https://openalex.org/W4400527749","doi":"https://doi.org/10.1109/fg59268.2024.10581865","title":"Attention Prompt Tuning: Parameter-efficient Adaptation of Pre-trained Models for Action Recognition","display_name":"Attention Prompt Tuning: Parameter-efficient Adaptation of Pre-trained Models for Action Recognition","publication_year":2024,"publication_date":"2024-05-27","ids":{"openalex":"https://openalex.org/W4400527749","doi":"https://doi.org/10.1109/fg59268.2024.10581865"},"language":"en","primary_location":{"id":"doi:10.1109/fg59268.2024.10581865","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/fg59268.2024.10581865","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)","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/A5027481493","display_name":"Wele Gedara Chaminda Bandara","orcid":"https://orcid.org/0000-0003-2516-2930"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wele Gedara Chaminda Bandara","raw_affiliation_strings":["Johns Hopkins University,Baltimore,Maryland,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,Maryland,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004716468","display_name":"Vishal M. Patel","orcid":"https://orcid.org/0000-0002-5239-692X"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vishal M. Patel","raw_affiliation_strings":["Johns Hopkins University,Baltimore,Maryland,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,Maryland,USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.7888,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76207551,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9807999730110168,"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":0.9807999730110168,"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":0.9763000011444092,"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":0.9440000057220459,"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/computer-science","display_name":"Computer science","score":0.7132914066314697},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6590203642845154},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.6176189184188843},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5023815631866455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4571395516395569},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3488210141658783},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3390875458717346},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0793900191783905},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.06533479690551758},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06272232532501221}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7132914066314697},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6590203642845154},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.6176189184188843},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5023815631866455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4571395516395569},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3488210141658783},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3390875458717346},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0793900191783905},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.06533479690551758},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06272232532501221},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fg59268.2024.10581865","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/fg59268.2024.10581865","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G770822966","display_name":null,"funder_award_id":"W911NF-21-2-0211","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2997567050","https://openalex.org/W1483272040","https://openalex.org/W4283377908","https://openalex.org/W1533421371","https://openalex.org/W2003050223","https://openalex.org/W2091777911","https://openalex.org/W2766405861","https://openalex.org/W2360975119","https://openalex.org/W1576128429","https://openalex.org/W2269464716"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,119,139],"introduce":[4,140],"Attention":[5],"Prompt":[6,24],"Tuning":[7],"(APT)":[8],"-":[9],"a":[10,29,63,141,168],"computationally":[11],"efficient":[12],"variant":[13],"of":[14,31,51,65,73,86,109,129,162],"prompt":[15,143],"tuning":[16,25,176],"for":[17,184],"video-based":[18],"applications":[19],"such":[20],"as":[21],"action":[22,185],"recognition.":[23,186],"approaches":[26],"involve":[27],"injecting":[28],"set":[30],"learnable":[32,52,66],"prompts":[33,67,88,123],"along":[34],"with":[35],"data":[36],"tokens":[37],"during":[38,113],"fine-tuning":[39],"while":[40,166],"keeping":[41],"the":[42,49,96,107,122,125,130,135,160,173],"backbone":[43],"frozen.":[44],"This":[45,94],"approach":[46,157],"greatly":[47,158],"reduces":[48,95,159],"number":[50,108,161],"parameters":[53],"compared":[54],"to":[55,71,89,146],"full":[56,74],"tuning.":[57,75],"For":[58],"image-based":[59],"downstream":[60],"tasks,":[61],"normally":[62],"couple":[64],"achieve":[68,90],"results":[69],"close":[70],"those":[72],"However,":[76],"videos,":[77],"which":[78],"contain":[79],"more":[80,149],"complex":[81],"spatiotemporal":[82],"information,":[83],"require":[84],"hundreds":[85],"tunable":[87],"reasonably":[91],"good":[92],"results.":[93],"parameter":[97],"efficiency":[98],"observed":[99],"in":[100],"images":[101],"and":[102,106,127,164,181,189],"significantly":[103],"increases":[104],"latency":[105,165],"floating-point":[110],"operations":[111],"(FLOPs)":[112],"inference.":[114],"To":[115],"tackle":[116],"these":[117],"issues,":[118],"directly":[120],"inject":[121],"into":[124],"keys":[126],"values":[128],"non-local":[131],"attention":[132],"mechanism":[133],"within":[134],"transformer":[136],"block.":[137],"Additionally,":[138],"novel":[142],"reparameterization":[144],"technique":[145],"make":[147],"APT":[148,156],"robust":[150],"against":[151],"hyperparameter":[152],"selection.":[153],"The":[154,187],"proposed":[155],"FLOPs":[163],"achieving":[167],"significant":[169],"performance":[170],"boost":[171],"over":[172],"existing":[174],"parameter-efficient":[175],"methods":[177],"on":[178],"UCF101,":[179],"HMDB51,":[180],"SSv2":[182],"datasets":[183],"code":[188],"pre-trained":[190],"models":[191],"are":[192],"available":[193],"at":[194],"https://github.com/wgcban/apt":[195]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}