{"id":"https://openalex.org/W4392904684","doi":"https://doi.org/10.1109/icassp48485.2024.10447548","title":"HaltingVT: Adaptive Token Halting Transformer for Efficient Video Recognition","display_name":"HaltingVT: Adaptive Token Halting Transformer for Efficient Video Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904684","doi":"https://doi.org/10.1109/icassp48485.2024.10447548"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5109996614","display_name":"Qian Wu","orcid":"https://orcid.org/0009-0006-2491-0035"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Wu","raw_affiliation_strings":["NetEase Yidun AI Lab,Hangzhou,China","NetEase Yidun AI Lab, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Yidun AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"NetEase Yidun AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042666275","display_name":"Ruoxuan Cui","orcid":"https://orcid.org/0000-0002-4789-6452"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruoxuan Cui","raw_affiliation_strings":["NetEase Yidun AI Lab,Hangzhou,China","NetEase Yidun AI Lab, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Yidun AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"NetEase Yidun AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100697204","display_name":"Yuke Li","orcid":"https://orcid.org/0009-0000-7282-8964"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuke Li","raw_affiliation_strings":["NetEase Yidun AI Lab,Hangzhou,China","NetEase Yidun AI Lab, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Yidun AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"NetEase Yidun AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012539121","display_name":"Haoqi Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoqi Zhu","raw_affiliation_strings":["NetEase Yidun AI Lab,Hangzhou,China","NetEase Yidun AI Lab, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Yidun AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"NetEase Yidun AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210091137"],"apc_list":null,"apc_paid":null,"fwci":1.2855,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79977845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4305","last_page":"4309"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9997000098228455,"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":0.9997000098228455,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9983000159263611,"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":0.9943000078201294,"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":0.8342041373252869},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.7195479869842529},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6763978004455566},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.661464273929596},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.36520659923553467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3521648049354553},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3212406039237976},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.2205648422241211},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.20709532499313354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8342041373252869},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.7195479869842529},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6763978004455566},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.661464273929596},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.36520659923553467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3521648049354553},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3212406039237976},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2205648422241211},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.20709532499313354},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2325237720","https://openalex.org/W2619947201","https://openalex.org/W2918626955","https://openalex.org/W2988630963","https://openalex.org/W3004505825","https://openalex.org/W3010010212","https://openalex.org/W3034658206","https://openalex.org/W3035141718","https://openalex.org/W3035682985","https://openalex.org/W3091825536","https://openalex.org/W3094502228","https://openalex.org/W3107849462","https://openalex.org/W3126721948","https://openalex.org/W3128170523","https://openalex.org/W3177141386","https://openalex.org/W3177399480","https://openalex.org/W3194477422","https://openalex.org/W3203618782","https://openalex.org/W3203903323","https://openalex.org/W3204647170","https://openalex.org/W4214612132","https://openalex.org/W4214661601","https://openalex.org/W4297411864","https://openalex.org/W4312266966","https://openalex.org/W4312302951","https://openalex.org/W4312560592","https://openalex.org/W4312849330","https://openalex.org/W4313171043","https://openalex.org/W4313192411","https://openalex.org/W4390872807","https://openalex.org/W6701498492","https://openalex.org/W6784333009","https://openalex.org/W6789558952","https://openalex.org/W6843227653","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W4315697128","https://openalex.org/W3102845713","https://openalex.org/W2971502891","https://openalex.org/W3205506801","https://openalex.org/W4388335561","https://openalex.org/W4280599700","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W4304700937"],"abstract_inverted_index":{"Action":[0],"recognition":[1,102],"in":[2,29,74,78,91,119,140],"videos":[3],"poses":[4],"a":[5,57,61,75,141],"challenge":[6],"due":[7],"to":[8,112],"its":[9],"high":[10],"computational":[11,81],"cost,":[12],"especially":[13],"for":[14,100],"Joint":[15,58],"Space-Time":[16],"video":[17,44,49,101,131],"transformers":[18],"(Joint":[19],"VT).":[20],"Despite":[21],"their":[22,34],"effectiveness,":[23],"the":[24,79,84,115,153],"excessive":[25],"number":[26],"of":[27,56],"tokens":[28,90],"such":[30],"architectures":[31],"significantly":[32],"limits":[33],"efficiency.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39,121,157],"propose":[40],"HaltingVT,":[41],"an":[42,123,172],"efficient":[43],"transformer":[45,93],"adaptively":[46],"removing":[47],"redundant":[48,89],"patch":[50],"tokens,":[51],"which":[52,95],"is":[53,179],"primarily":[54],"composed":[55],"VT":[59],"and":[60,134],"Glimpser":[62,85],"module.":[63],"Specifically,":[64],"HaltingVT":[65,111,129],"applies":[66],"data-adaptive":[67],"token":[68,135],"reduction":[69,77],"at":[70,181],"each":[71],"layer,":[72],"resulting":[73],"significant":[76],"overall":[80],"cost.":[82],"Besides,":[83],"module":[86],"quickly":[87],"removes":[88],"shallow":[92],"layers,":[94],"may":[96],"even":[97],"be":[98],"misleading":[99],"tasks":[103],"based":[104],"on":[105,114],"our":[106],"observations.":[107],"To":[108],"further":[109],"encourage":[110],"focus":[113],"key":[116],"motion-related":[117],"information":[118],"videos,":[120],"design":[122],"effective":[124],"Motion":[125],"Loss":[126],"during":[127],"training.":[128],"acquires":[130],"analysis":[132],"capabilities":[133],"halting":[136],"compression":[137],"strategies":[138],"simultaneously":[139],"unified":[142],"training":[143,148],"process,":[144],"without":[145],"requiring":[146],"additional":[147],"procedures":[149],"or":[150],"sub-networks.":[151],"On":[152],"Mini-Kinetics":[154],"dataset":[155],"[1],":[156],"achieved":[158],"75.0%":[159],"top-1":[160,169],"ACC":[161,170],"with":[162,171],"24.2":[163],"GFLOPs,":[164],"as":[165,167],"well":[166],"67.2%":[168],"extremely":[173],"low":[174],"9.9":[175],"GFLOPs.":[176],"The":[177],"code":[178],"available":[180],"https://github.com/dun-research/HaltingVT.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}