{"id":"https://openalex.org/W4416830902","doi":"https://doi.org/10.48550/arxiv.2509.22481","title":"PSTTS: A Plug-and-Play Token Selector for Efficient Event-based Spatio-temporal Representation Learning","display_name":"PSTTS: A Plug-and-Play Token Selector for Efficient Event-based Spatio-temporal Representation Learning","publication_year":2025,"publication_date":"2025-09-26","ids":{"openalex":"https://openalex.org/W4416830902","doi":"https://doi.org/10.48550/arxiv.2509.22481"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2509.22481","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.22481","pdf_url":"https://arxiv.org/pdf/2509.22481","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.22481","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059374249","display_name":"Xiangmo Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhao, Xiangmo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072808499","display_name":"Nan Yang","orcid":"https://orcid.org/0000-0002-2621-8927"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Nan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119268791","display_name":"Yang Wang","orcid":"https://orcid.org/0009-0001-5770-0126"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034196914","display_name":"Zhanwen Liu","orcid":"https://orcid.org/0000-0002-8823-0833"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhanwen","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059374249"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.8913000226020813,"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":0.8913000226020813,"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":0.014499999582767487,"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":0.011900000274181366,"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/security-token","display_name":"Security token","score":0.6675000190734863},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.58160001039505},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5396999716758728},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.41609999537467957},{"id":"https://openalex.org/keywords/subnetwork","display_name":"Subnetwork","score":0.396699994802475},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.3869999945163727},{"id":"https://openalex.org/keywords/token-passing","display_name":"Token passing","score":0.38179999589920044},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.337799996137619}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7864999771118164},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6675000190734863},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.58160001039505},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5396999716758728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5090000033378601},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.41609999537467957},{"id":"https://openalex.org/C2780186347","wikidata":"https://www.wikidata.org/wiki/Q11414","display_name":"Subnetwork","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3898000121116638},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C115067241","wikidata":"https://www.wikidata.org/wiki/Q1639854","display_name":"Token passing","level":3,"score":0.38179999589920044},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32839998602867126},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32249999046325684},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2985999882221222},{"id":"https://openalex.org/C179800331","wikidata":"https://www.wikidata.org/wiki/Q15260703","display_name":"Event tree analysis","level":3,"score":0.2874999940395355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.28119999170303345},{"id":"https://openalex.org/C39394851","wikidata":"https://www.wikidata.org/wiki/Q921594","display_name":"Inter frame","level":4,"score":0.2766000032424927},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2509.22481","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.22481","pdf_url":"https://arxiv.org/pdf/2509.22481","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.22481","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.22481","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.22481","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.22481","pdf_url":"https://arxiv.org/pdf/2509.22481","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Mainstream":[0],"event-based":[1],"spatio-temporal":[2,95,108,143],"representation":[3],"learning":[4],"methods":[5,45],"typically":[6],"process":[7],"event":[8,16,34,60,69,85,101,149,169],"streams":[9],"by":[10,140,210,215],"converting":[11],"them":[12,63],"into":[13],"sequences":[14],"of":[15,59,122,145],"frames,":[17,170],"achieving":[18,111],"remarkable":[19],"performance.":[20],"However,":[21],"they":[22],"neglect":[23,56],"the":[24,57,94,142,163,191,218],"high":[25],"spatial":[26],"sparsity":[27],"and":[28,55,106,117,128,137,173,188,194,212],"inter-frame":[29],"motion":[30,164],"redundancy":[31,157],"inherent":[32],"in":[33,99],"frame":[35,150],"sequences,":[36],"leading":[37],"to":[38,68,103,151,181],"significant":[39,203],"computational":[40],"overhead.":[41],"Existing":[42],"token":[43,53],"sparsification":[44],"for":[46,65,84],"RGB":[47],"videos":[48],"rely":[49],"on":[50,190,217],"unreliable":[51],"intermediate":[52],"representations":[54],"influence":[58],"noise,":[61],"making":[62],"ineffective":[64],"direct":[66],"application":[67],"data.":[70],"In":[71],"this":[72],"paper,":[73],"we":[74],"propose":[75],"Progressive":[76],"Spatio-Temporal":[77],"Token":[78,126,130,133,160],"Selection":[79,161],"(PSTTS),":[80],"a":[81],"Plug-and-Play":[82],"module":[83],"data":[86,102],"without":[87],"introducing":[88],"any":[89],"additional":[90],"parameters.":[91],"PSTTS":[92,120,180,201,207],"exploits":[93],"distribution":[96],"characteristics":[97],"embedded":[98],"raw":[100],"effectively":[104],"identify":[105],"discard":[107],"redundant":[109,175],"tokens,":[110],"an":[112],"optimal":[113],"trade-off":[114],"between":[115,167],"accuracy":[116],"efficiency.":[118],"Specifically,":[119,206],"consists":[121],"two":[123],"stages,":[124],"Spatial":[125,132],"Purification":[127,134],"Temporal":[129,159],"Selection.":[131],"discards":[135],"noise":[136],"non-event":[138],"regions":[139],"assessing":[141],"consistency":[144],"events":[146],"within":[147],"each":[148],"prevent":[152],"interference":[153],"with":[154],"subsequent":[155],"temporal":[156,176],"evaluation.":[158],"evaluates":[162],"pattern":[165],"similarity":[166],"adjacent":[168],"precisely":[171],"identifying":[172],"removing":[174],"information.":[177],"We":[178],"apply":[179],"four":[182],"representative":[183],"backbones":[184],"UniformerV2,":[185],"VideoSwin,":[186],"EVMamba,":[187],"ExACT":[189],"HARDVS,":[192],"DailyDVS-200,":[193],"SeACT":[195],"datasets.":[196],"Experimental":[197],"results":[198],"demonstrate":[199],"that":[200],"achieves":[202],"efficiency":[204],"improvements.":[205],"reduces":[208],"FLOPs":[209],"29-43.6%":[211],"increases":[213],"FPS":[214],"21.6-41.3%":[216],"DailyDVS-200":[219],"dataset,":[220],"while":[221],"maintaining":[222],"task":[223],"accuracy.":[224],"Our":[225],"code":[226],"will":[227],"be":[228],"available.":[229]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}