{"id":"https://openalex.org/W4405180659","doi":"https://doi.org/10.1109/tpami.2024.3514654","title":"Uni-AdaFocus: Spatial-Temporal Dynamic Computation for Video Recognition","display_name":"Uni-AdaFocus: Spatial-Temporal Dynamic Computation for Video Recognition","publication_year":2024,"publication_date":"2024-12-09","ids":{"openalex":"https://openalex.org/W4405180659","doi":"https://doi.org/10.1109/tpami.2024.3514654","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030449"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3514654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3514654","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100418037","display_name":"Yulin Wang","orcid":"https://orcid.org/0000-0002-1363-0234"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulin Wang","raw_affiliation_strings":["Department of Automation, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1363-0234","affiliations":[{"raw_affiliation_string":"Department of Automation, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019012787","display_name":"Haoji Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoji Zhang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Yue","orcid":"https://orcid.org/0009-0005-3155-1336"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yue","raw_affiliation_strings":["Department of Automation, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-3155-1336","affiliations":[{"raw_affiliation_string":"Department of Automation, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101868179","display_name":"Shiji Song","orcid":"https://orcid.org/0000-0003-0858-1770"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiji Song","raw_affiliation_strings":["Department of Automation, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0858-1770","affiliations":[{"raw_affiliation_string":"Department of Automation, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110674447","display_name":"Chao Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Deng","raw_affiliation_strings":["China Mobile Research Institute, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute, Beijing, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079750750","display_name":"Junlan Feng","orcid":"https://orcid.org/0000-0001-5292-2945"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junlan Feng","raw_affiliation_strings":["China Mobile Research Institute, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute, Beijing, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013240918","display_name":"Gao Huang","orcid":"https://orcid.org/0000-0002-7251-0988"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao Huang","raw_affiliation_strings":["Department of Automation, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7251-0988","affiliations":[{"raw_affiliation_string":"Department of Automation, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8393,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.87014641,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"47","issue":"3","first_page":"1782","last_page":"1799"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"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":0.7122087478637695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6732600927352905},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5781434774398804},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.537621796131134},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5366935133934021},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1828502118587494}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7122087478637695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6732600927352905},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5781434774398804},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.537621796131134},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5366935133934021},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1828502118587494}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3514654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3514654","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40030449","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030449","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2438210826","display_name":null,"funder_award_id":"62321005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5313418749","display_name":null,"funder_award_id":"42327901","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":126,"referenced_works":["https://openalex.org/W62603772","https://openalex.org/W1522734439","https://openalex.org/W1777628566","https://openalex.org/W1923404803","https://openalex.org/W1927052826","https://openalex.org/W1947481528","https://openalex.org/W2040367556","https://openalex.org/W2064675550","https://openalex.org/W2096343094","https://openalex.org/W2156342794","https://openalex.org/W2194775991","https://openalex.org/W2295107390","https://openalex.org/W2338447355","https://openalex.org/W2342662179","https://openalex.org/W2507009361","https://openalex.org/W2552900565","https://openalex.org/W2562731582","https://openalex.org/W2619947201","https://openalex.org/W2625366777","https://openalex.org/W2736601468","https://openalex.org/W2737725206","https://openalex.org/W2746726611","https://openalex.org/W2766988981","https://openalex.org/W2770804203","https://openalex.org/W2799176631","https://openalex.org/W2806331055","https://openalex.org/W2807968599","https://openalex.org/W2883429621","https://openalex.org/W2895243423","https://openalex.org/W2895738954","https://openalex.org/W2906155095","https://openalex.org/W2929084559","https://openalex.org/W2929753309","https://openalex.org/W2945472816","https://openalex.org/W2950635152","https://openalex.org/W2962858109","https://openalex.org/W2962865604","https://openalex.org/W2962934715","https://openalex.org/W2963091558","https://openalex.org/W2963155035","https://openalex.org/W2963163009","https://openalex.org/W2963321993","https://openalex.org/W2963524571","https://openalex.org/W2963645879","https://openalex.org/W2963896595","https://openalex.org/W2981385151","https://openalex.org/W2984287396","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W2992457155","https://openalex.org/W2996901793","https://openalex.org/W3000097396","https://openalex.org/W3004505825","https://openalex.org/W3004606649","https://openalex.org/W3010010212","https://openalex.org/W3011398234","https://openalex.org/W3012362498","https://openalex.org/W3034572008","https://openalex.org/W3034600407","https://openalex.org/W3034658206","https://openalex.org/W3034768625","https://openalex.org/W3035303837","https://openalex.org/W3035424951","https://openalex.org/W3035678286","https://openalex.org/W3036001641","https://openalex.org/W3091825536","https://openalex.org/W3107849462","https://openalex.org/W3109632933","https://openalex.org/W3126721948","https://openalex.org/W3135384301","https://openalex.org/W3136986393","https://openalex.org/W3156973125","https://openalex.org/W3160264863","https://openalex.org/W3172990466","https://openalex.org/W3173621652","https://openalex.org/W3175528717","https://openalex.org/W3177141386","https://openalex.org/W3177399480","https://openalex.org/W3186033197","https://openalex.org/W3194360768","https://openalex.org/W3194477422","https://openalex.org/W3198602280","https://openalex.org/W3200435621","https://openalex.org/W3203618782","https://openalex.org/W3203903323","https://openalex.org/W3204647170","https://openalex.org/W3210279979","https://openalex.org/W4206046172","https://openalex.org/W4206481149","https://openalex.org/W4206774749","https://openalex.org/W4214612132","https://openalex.org/W4214661601","https://openalex.org/W4214727094","https://openalex.org/W4226146163","https://openalex.org/W4290714341","https://openalex.org/W4298857966","https://openalex.org/W4312253723","https://openalex.org/W4312266966","https://openalex.org/W4312302951","https://openalex.org/W4312560592","https://openalex.org/W4312681772","https://openalex.org/W4312749457","https://openalex.org/W4313171043","https://openalex.org/W4317038436","https://openalex.org/W4362500802","https://openalex.org/W4379185441","https://openalex.org/W4388811524","https://openalex.org/W6618372016","https://openalex.org/W6629606793","https://openalex.org/W6637967152","https://openalex.org/W6674238660","https://openalex.org/W6682137061","https://openalex.org/W6741002519","https://openalex.org/W6745447533","https://openalex.org/W6761274798","https://openalex.org/W6762718338","https://openalex.org/W6766978945","https://openalex.org/W6767312631","https://openalex.org/W6770390784","https://openalex.org/W6784233108","https://openalex.org/W6784333009","https://openalex.org/W6789558952","https://openalex.org/W6802919969","https://openalex.org/W6802996638","https://openalex.org/W6846522197","https://openalex.org/W6955071965"],"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":{"This":[0],"paper":[1],"presents":[2],"a":[3,48,72,78,88,107,123,212,270],"comprehensive":[4,213],"exploration":[5],"of":[6,9,28,154,190,230,234],"the":[7,16,34,37,67,97,112,117,128,145,152,180,188,193,200,228,328],"phenomenon":[8],"data":[10],"redundancy":[11],"in":[12,41,138,159,232],"video":[13,43,81,99,196],"understanding,":[14],"with":[15,25,252,308],"aim":[17],"to":[18,33,47,94,110,192],"improve":[19],"computational":[20,273],"efficiency.":[21,274],"Our":[22,207],"investigation":[23],"commences":[24],"an":[26,139],"examination":[27],"spatial":[29],"redundancy,":[30],"which":[31,260],"refers":[32],"observation":[35],"that":[36,171,215,321],"most":[38,113,194],"informative":[39,146],"region":[40],"each":[42],"frame":[44],"usually":[45],"corresponds":[46],"small":[49],"image":[50],"patch,":[51],"whose":[52,101],"shape,":[53],"size":[54],"and":[55,76,182,198,220,238,246,258,291,293,304,314,332,339],"location":[56],"shift":[57],"smoothly":[58],"across":[59],"frames.":[60],"Motivated":[61],"by":[62,106,122,177],"this":[63],"phenomenon,":[64],"we":[65,169],"formulate":[66],"patch":[68,147],"localization":[69],"problem":[70],"as":[71,248,265],"dynamic":[73,223],"decision":[74],"task,":[75],"introduce":[77],"spatially":[79],"adaptive":[80],"recognition":[82,316],"approach,":[83],"termed":[84],"AdaFocus.":[85],"In":[86,241],"specific,":[87],"lightweight":[89],"encoder":[90],"is":[91,244,250,323],"first":[92],"employed":[93],"quickly":[95],"process":[96],"full":[98],"sequence,":[100],"features":[102],"are":[103,120,335],"then":[104],"utilized":[105],"policy":[108],"network":[109,126],"identify":[111],"task-relevant":[114,195],"regions.":[115],"Subsequently,":[116],"selected":[118],"patches":[119],"inferred":[121],"high-capacity":[124],"deep":[125],"for":[127,317],"final":[129],"prediction.":[130],"The":[131],"complete":[132],"model":[133],"can":[134,156,173,261],"be":[135,157,174,262],"trained":[136],"conveniently":[137],"end-to-end":[140,236],"manner.":[141],"During":[142],"inference,":[143],"once":[144],"sequence":[148],"has":[149],"been":[150],"generated,":[151],"bulk":[153],"computation":[155,191,201],"executed":[158],"parallel,":[160],"rendering":[161],"it":[162,226,249],"efficient":[163,235,326],"on":[164,203,279],"modern":[165],"GPU":[166],"devices.":[167],"Furthermore,":[168],"demonstrate":[170],"AdaFocus":[172,231],"easily":[175],"extended":[176],"further":[178],"considering":[179],"temporal":[181],"sample-":[183,221],"wise":[184,222],"redundancies,":[185],"i.e.,":[186],"allocating":[187],"majority":[189],"frames,":[197],"minimizing":[199],"spent":[202],"relatively":[204],"\"easier\"":[205],"videos.":[206],"resulting":[208],"algorithm,":[209],"Uni-AdaFocus,":[210],"establishes":[211],"framework":[214],"seamlessly":[216],"integrates":[217],"spatial,":[218],"temporal,":[219],"computation,":[224],"while":[225],"preserves":[227],"merits":[229],"terms":[233],"training":[237],"hardware":[239],"friendliness.":[240],"addition,":[242],"Uni-AdaFocus":[243,322],"general":[245],"flexible":[247],"compatible":[251],"off-the-shelf":[253],"backbone":[254],"models":[255,334],"(e.g.,":[256],"TSM":[257],"X3D),":[259],"readily":[263],"deployed":[264],"our":[266],"feature":[267],"extractor,":[268],"yielding":[269],"significantly":[271],"improved":[272],"Empirically,":[275],"extensive":[276],"experiments":[277],"based":[278],"seven":[280],"widely-used":[281],"benchmark":[282],"datasets":[283],"(i.e.,":[284,298],"ActivityNet,":[285],"FCVID,":[286],"Mini-Kinetics,":[287],"Something-Something":[288],"V1&V2,":[289],"Jester,":[290],"Kinetics-400)":[292],"three":[294],"real-world":[295],"application":[296],"scenarios":[297],"fine-grained":[299],"diving":[300],"action":[301],"classification,":[302],"Alzheimer's":[303],"Parkinson's":[305],"diseases":[306],"diagnosis":[307],"brain":[309],"magnetic":[310],"resonance":[311],"images":[312],"(MRI),":[313],"violence":[315],"online":[318],"videos)":[319],"substantiate":[320],"considerably":[324],"more":[325],"than":[327],"competitive":[329],"baselines.":[330],"Code":[331],"pre-trained":[333],"available":[336],"at":[337],"https://github.com/blackfeather-wang/AdaFocus":[338],"https://github.com/LeapLabTHU/AdaFocusV2.":[340]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}