{"id":"https://openalex.org/W3015428919","doi":"https://doi.org/10.1109/icassp40776.2020.9054394","title":"Enhanced Action Tubelet Detector for Spatio-Temporal Video Action Detection","display_name":"Enhanced Action Tubelet Detector for Spatio-Temporal Video Action Detection","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015428919","doi":"https://doi.org/10.1109/icassp40776.2020.9054394","mag":"3015428919"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5065019651","display_name":"Yutang Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yutang Wu","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058982350","display_name":"Hanli Wang","orcid":"https://orcid.org/0000-0002-9999-4871"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanli Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101797017","display_name":"Shuheng Wang","orcid":"https://orcid.org/0009-0005-4107-5038"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuheng Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119247506","display_name":"Qinyu Li","orcid":"https://orcid.org/0009-0001-1519-0914"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinyu Li","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5065019651"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.1954,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.47302884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2388","last_page":"2392"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991000294685364,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9973999857902527,"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/rgb-color-model","display_name":"RGB color model","score":0.8066078424453735},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7856773138046265},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.7242639064788818},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.6272586584091187},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.5460481643676758},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5140272378921509},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49498528242111206},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.44392645359039307},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.37958455085754395},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.138638436794281},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1347048580646515},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.10189178586006165}],"concepts":[{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.8066078424453735},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7856773138046265},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.7242639064788818},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.6272586584091187},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.5460481643676758},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5140272378921509},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49498528242111206},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.44392645359039307},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.37958455085754395},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.138638436794281},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1347048580646515},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.10189178586006165}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W639708223","https://openalex.org/W1797109199","https://openalex.org/W1923332106","https://openalex.org/W2034014085","https://openalex.org/W2102605133","https://openalex.org/W2131311058","https://openalex.org/W2156303437","https://openalex.org/W2505004417","https://openalex.org/W2519080876","https://openalex.org/W2570343428","https://openalex.org/W2605111198","https://openalex.org/W2611596598","https://openalex.org/W2613718673","https://openalex.org/W2727849499","https://openalex.org/W2890968638","https://openalex.org/W2933966997","https://openalex.org/W2949343965","https://openalex.org/W2962722947","https://openalex.org/W2962803561","https://openalex.org/W2963529931","https://openalex.org/W2964207322","https://openalex.org/W3106250896","https://openalex.org/W6620707391","https://openalex.org/W6679761776","https://openalex.org/W6682864246","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W4389449520","https://openalex.org/W127192698","https://openalex.org/W2570600173","https://openalex.org/W2893008024","https://openalex.org/W2743735673","https://openalex.org/W4361801939","https://openalex.org/W2360131081","https://openalex.org/W2985941356","https://openalex.org/W2802243998","https://openalex.org/W1521014365"],"abstract_inverted_index":{"Current":[0],"spatio-temporal":[1],"action":[2,52,101],"detection":[3],"methods":[4,118],"usually":[5],"employ":[6],"a":[7,10,46,132],"two-stream":[8,117],"architecture,":[9,135],"RGB":[11,41,63,72,110],"stream":[12,20,30,48,111],"for":[13,21,28],"raw":[14],"images":[15],"and":[16,31,84,91,112,151],"an":[17],"auxiliary":[18],"motion":[19],"optical":[22,82],"flow.":[23],"Training":[24],"is":[25,56,68,89,113],"required":[26],"individually":[27],"each":[29],"more":[32],"efforts":[33],"are":[34],"necessary":[35],"to":[36,70,115],"improve":[37],"the":[38,78,92,122,136,145],"precision":[39],"of":[40,81,124],"stream.":[42,64],"To":[43],"this":[44,59],"end,":[45],"single":[47],"network":[49,88],"named":[50],"enhanced":[51],"tubelet":[53],"(EAT)":[54],"detector":[55,107,140],"proposed":[57,93],"in":[58,131],"work":[60],"based":[61],"on":[62,148],"A":[65],"modulation":[66],"layer":[67,94],"designed":[69],"modulate":[71],"features":[73],"with":[74],"conditional":[75],"information":[76],"from":[77,121],"visual":[79],"clues":[80],"flow":[83],"human":[85],"pose.":[86],"This":[87],"end-to-end":[90],"can":[95],"be":[96],"easily":[97],"applied":[98],"into":[99],"other":[100],"detectors.":[102],"Experiments":[103],"show":[104],"that":[105],"EAT":[106,139],"outperforms":[108],"traditional":[109],"competitive":[114],"existing":[116],"while":[119],"free":[120],"trouble":[123],"training":[125],"streams":[126],"separately.":[127],"By":[128],"being":[129],"embedded":[130],"new":[133],"three-stream":[134,138],"resulting":[137],"achieves":[141],"impressive":[142],"performances":[143],"among":[144],"best":[146],"competitors":[147],"UCF-Sports,":[149],"JHMDB":[150],"UCF-101.":[152]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}