{"id":"https://openalex.org/W2922259464","doi":"https://doi.org/10.1109/wacv.2019.00013","title":"Video Action Recognition With an Additional End-to-End Trained Temporal Stream","display_name":"Video Action Recognition With an Additional End-to-End Trained Temporal Stream","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2922259464","doi":"https://doi.org/10.1109/wacv.2019.00013","mag":"2922259464"},"language":"en","primary_location":{"id":"doi:10.1109/wacv.2019.00013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv.2019.00013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1573164","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089801879","display_name":"Guojing Cong","orcid":"https://orcid.org/0000-0003-0850-7714"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Guojing Cong","raw_affiliation_strings":["IBM Thomas J. Watson Research Center"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084939540","display_name":"Giacomo Domeniconi","orcid":"https://orcid.org/0000-0003-2797-1547"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Giacomo Domeniconi","raw_affiliation_strings":["IBM Thomas J. Watson Research Center"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076769170","display_name":"Joshua Shapiro","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua Shapiro","raw_affiliation_strings":["IBM Thomas J. Watson Research Center"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101738461","display_name":"Chih-Chieh Yang","orcid":"https://orcid.org/0000-0003-2816-4464"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chih-Chieh Yang","raw_affiliation_strings":["ASAPP"],"affiliations":[{"raw_affiliation_string":"ASAPP","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067651004","display_name":"Barry Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barry Chen","raw_affiliation_strings":["Lawrence Livermore National Laboratory"],"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory","institution_ids":["https://openalex.org/I1282311441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5089801879"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":0.5109,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.68264959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"14","issue":null,"first_page":"51","last_page":"60"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9990000128746033,"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":0.9945999979972839,"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":0.872051477432251},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.636502742767334},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.573749303817749},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.5611124038696289},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5523650050163269},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5446616411209106},{"id":"https://openalex.org/keywords/temporal-database","display_name":"Temporal database","score":0.5425879955291748},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.49211782217025757},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4912840723991394},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4732654094696045},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33688071370124817},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3066730499267578},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2771841883659363},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13844475150108337}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.872051477432251},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.636502742767334},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.573749303817749},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.5611124038696289},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5523650050163269},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5446616411209106},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.5425879955291748},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.49211782217025757},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4912840723991394},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4732654094696045},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33688071370124817},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3066730499267578},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2771841883659363},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13844475150108337},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wacv.2019.00013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv.2019.00013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1573164","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1573164","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1573164","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1573164","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W787785461","https://openalex.org/W1513100184","https://openalex.org/W1586730761","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1923404803","https://openalex.org/W1947481528","https://openalex.org/W1983364832","https://openalex.org/W2016053056","https://openalex.org/W2096621047","https://openalex.org/W2097117768","https://openalex.org/W2117539524","https://openalex.org/W2122476475","https://openalex.org/W2126579184","https://openalex.org/W2156303437","https://openalex.org/W2194775991","https://openalex.org/W2342662179","https://openalex.org/W2507009361","https://openalex.org/W2548527721","https://openalex.org/W2560474170","https://openalex.org/W2563717578","https://openalex.org/W2604128149","https://openalex.org/W2605111198","https://openalex.org/W2618530766","https://openalex.org/W2619947201","https://openalex.org/W2746726611","https://openalex.org/W2747141180","https://openalex.org/W2773514261","https://openalex.org/W2950971447","https://openalex.org/W2951183276","https://openalex.org/W2951864506","https://openalex.org/W2953084276","https://openalex.org/W2962835968","https://openalex.org/W2963037989","https://openalex.org/W3102816259","https://openalex.org/W4237044863","https://openalex.org/W6600983433","https://openalex.org/W6622789128","https://openalex.org/W6630726011","https://openalex.org/W6637373629","https://openalex.org/W6682864246","https://openalex.org/W6687483927","https://openalex.org/W6689710714","https://openalex.org/W6724944384","https://openalex.org/W6731097996","https://openalex.org/W6736349848","https://openalex.org/W6747225971","https://openalex.org/W6785938674","https://openalex.org/W6800482781"],"related_works":["https://openalex.org/W4297270893","https://openalex.org/W4303411729","https://openalex.org/W2577671007","https://openalex.org/W1591216093","https://openalex.org/W3091300685","https://openalex.org/W2912100719","https://openalex.org/W2331280411","https://openalex.org/W2963330455","https://openalex.org/W2783931899","https://openalex.org/W4211202157"],"abstract_inverted_index":{"Detecting":[0],"actions":[1],"in":[2,33,112],"videos":[3],"requires":[4],"understanding":[5],"the":[6,40,83,117,135,174],"temporal":[7,23,41,93,114,126,167],"relationships":[8],"among":[9],"frames.":[10],"Typical":[11],"action":[12],"recognition":[13],"approaches":[14],"rely":[15],"on":[16,142,152],"optical":[17,36],"flow":[18,37],"estimation":[19],"methods":[20],"to":[21,25,35,38,65,105,171],"convey":[22],"information":[24],"a":[26,89,100],"CNN.":[27],"Recent":[28],"studies":[29],"employ":[30],"3D":[31,175],"convolutions":[32],"addition":[34],"process":[39],"information.":[42],"While":[43],"these":[44,160],"models":[45],"achieve":[46,159],"slightly":[47],"better":[48],"results":[49,161],"than":[50,124,173],"two-stream":[51],"2D":[52,85,91],"convolutional":[53,92],"approaches,":[54],"they":[55],"are":[56],"significantly":[57],"more":[58,61,123],"complex,":[59],"requiring":[60],"data":[62],"and":[63,144,166],"time":[64],"be":[66],"trained.":[67],"We":[68,87,158],"propose":[69],"an":[70],"efficient,":[71],"adaptive":[72],"batch":[73],"size":[74],"distributed":[75],"training":[76,82,111],"algorithm":[77],"with":[78,99,122],"customized":[79],"optimizations":[80],"for":[81],"two":[84],"streams.":[86,127],"introduce":[88],"new":[90],"stream":[94,115],"that":[95,130,148],"is":[96],"trained":[97],"end-to-end":[98],"neural":[101],"network.":[102],"The":[103],"flexibility":[104],"freeze":[106],"some":[107],"network":[108],"layers":[109],"from":[110],"this":[113],"brings":[116],"possibility":[118],"of":[119,141],"ensemble":[120],"learning":[121],"one":[125],"Our":[128],"architecture":[129],"combines":[131],"three":[132],"streams":[133,168],"achieves":[134],"highest":[136],"accuracies":[137],"as":[138],"we":[139],"know":[140],"UCF101":[143],"HMDB51":[145],"by":[146],"systems":[147],"do":[149],"not":[150],"pretrain":[151],"much":[153],"larger":[154],"datasets":[155],"(e.g.,":[156],"Kinetics).":[157],"while":[162],"keeping":[163],"our":[164],"spatial":[165],"4.67x":[169],"faster":[170],"train":[172],"convolution":[176],"approaches.":[177]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}