{"id":"https://openalex.org/W2996152665","doi":"https://doi.org/10.1145/3368926.3369726","title":"Spatio-temporal Multi-level Fusion for Human Action Recognition","display_name":"Spatio-temporal Multi-level Fusion for Human Action Recognition","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2996152665","doi":"https://doi.org/10.1145/3368926.3369726","mag":"2996152665"},"language":"en","primary_location":{"id":"doi:10.1145/3368926.3369726","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3368926.3369726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth International Symposium on Information and Communication Technology  - SoICT 2019","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/A5021939682","display_name":"Manh-Hung Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Manh-Hung Lu","raw_affiliation_strings":["DS Lab, SoICT, HUST, Viettel High Technology Industries Corporation (VHT), Viettel Group Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"DS Lab, SoICT, HUST, Viettel High Technology Industries Corporation (VHT), Viettel Group Hanoi, Vietnam","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107427910","display_name":"Thi-Oanh Nguyen","orcid":"https://orcid.org/0000-0002-6166-2011"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Thi-Oanh Nguyen","raw_affiliation_strings":["DS Lab, SoICT, HUST, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"DS Lab, SoICT, HUST, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021939682"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2024,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55860648,"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":"298","last_page":"305"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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":1.0,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9933000206947327,"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":0.8227554559707642},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6362226605415344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5889334678649902},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5571597218513489},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5232416987419128},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.44518113136291504},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.43935853242874146},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4327702522277832},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39447474479675293},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32154595851898193}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8227554559707642},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6362226605415344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5889334678649902},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5571597218513489},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5232416987419128},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.44518113136291504},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.43935853242874146},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4327702522277832},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39447474479675293},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32154595851898193},{"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3368926.3369726","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3368926.3369726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth International Symposium on Information and Communication Technology  - SoICT 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1522734439","https://openalex.org/W2020682184","https://openalex.org/W2068611653","https://openalex.org/W2097117768","https://openalex.org/W2105101328","https://openalex.org/W2128730107","https://openalex.org/W2183341477","https://openalex.org/W2746726611","https://openalex.org/W2774324727","https://openalex.org/W2796633859","https://openalex.org/W2952186347","https://openalex.org/W2963315828","https://openalex.org/W2963524571","https://openalex.org/W2964094092","https://openalex.org/W4244838657"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3031039437","https://openalex.org/W3095877357","https://openalex.org/W183202219","https://openalex.org/W2072565696","https://openalex.org/W10861731","https://openalex.org/W2551337514"],"abstract_inverted_index":{"Two-stream":[0],"convolutional":[1],"networks":[2],"have":[3],"achieved":[4,158],"great":[5],"success":[6],"for":[7,109,163],"action":[8,82,91],"recognition":[9],"tasks.":[10],"In":[11,120,178],"this":[12],"paper,":[13],"we":[14,77,106,124],"propose":[15,107],"a":[16,74,190],"spatiotemporal":[17],"network":[18,196,214],"that":[19],"integrates":[20,50],"the":[21,30,89,100,104,121,140,145,151,182],"spatial":[22,33,67,164],"and":[23,34,115,127,208],"temporal":[24,35,62],"features":[25,79],"at":[26,53,73],"multi-level":[27,185],"to":[28,66,87,96,138,171,188],"model":[29,40,49,157,192],"correlation":[31],"between":[32],"information.":[36],"Based":[37],"on":[38,144],"TSN":[39,168],"[16]":[41],"where":[42],"videos":[43],"are":[44],"divided":[45],"into":[46,98],"segments,":[47,105],"our":[48],"spatio-temporal":[51],"information":[52,63],"either":[54],"local":[55,60],"or":[56],"global":[57,75,199],"levels.":[58],"At":[59],"levels,":[61],"is":[64],"transferred":[65],"stream":[68],"in":[69,94,193,206,210],"each":[70],"segment.":[71],"Considering":[72],"level,":[76],"integrate":[78],"of":[80,103,153,161,184,204,223],"entire":[81],"extracted":[83],"from":[84],"two":[85],"streams":[86],"obtain":[88],"final":[90],"representation.":[92],"Moreover,":[93],"order":[95],"take":[97],"consideration":[99],"chronological":[101],"sequence":[102],"strategies":[108,130],"segment":[110,172],"aggregation":[111,173],"by":[112],"using":[113,197],"Conv3D":[114],"LSTM":[116,176],"(Long-short":[117],"term":[118],"memory).":[119],"training":[122],"process,":[123],"also":[125,216],"applied":[126],"evaluated":[128],"several":[129],"such":[131],"as":[132],"auxiliary":[133],"classifier,":[134],"cross":[135],"modality":[136],"initialization":[137],"improve":[139],"convergence":[141],"rate.":[142],"Experimentation":[143],"standard":[146],"dataset":[147],"UCF-101":[148],"(split-1)":[149],"demonstrates":[150],"effectiveness":[152],"proposed":[154,179],"network.":[155],"Our":[156,212],"an":[159,202,221],"accuracy":[160,207,222],"87.1%":[162],"network,":[165,181],"higher":[166],"than":[167],"(85.5%)":[169],"thanks":[170],"strategy":[174,183],"with":[175,195,201,220],"seq-to-seq.":[177],"two-stream":[180,213],"fusion":[186,200],"allows":[187],"get":[189],"better":[191],"comparing":[194],"only":[198],"improvement":[203],"1.4%":[205],"1.2%":[209],"F1-score.":[211],"obtained":[215],"very":[217],"promising":[218],"results":[219],"92.57%.":[224]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}