{"id":"https://openalex.org/W3003109291","doi":"https://doi.org/10.1117/12.2559268","title":"Learning bag of spatio-temporal features for human interaction recognition","display_name":"Learning bag of spatio-temporal features for human interaction recognition","publication_year":2020,"publication_date":"2020-01-31","ids":{"openalex":"https://openalex.org/W3003109291","doi":"https://doi.org/10.1117/12.2559268","mag":"3003109291"},"language":"en","primary_location":{"id":"doi:10.1117/12.2559268","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2559268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Twelfth International Conference on Machine Vision (ICMV 2019)","raw_type":"proceedings-article"},"type":"preprint","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/A5055175308","display_name":"Khadidja Nour el Houda Slimani","orcid":null},"institutions":[{"id":"https://openalex.org/I157169809","display_name":"University of Sciences and Technology Houari Boumediene","ror":"https://ror.org/02kb89c09","country_code":"DZ","type":"education","lineage":["https://openalex.org/I157169809"]}],"countries":["DZ"],"is_corresponding":true,"raw_author_name":"Khadidja Nour el houda SLIMANI","raw_affiliation_strings":["Univ. of Sciences and Technology Houari Boumediene (Algeria)","D\u00e9partement d'Informatique, Laboratoire RIIMA, USTHB (Laboratoire RIIMA - D\u00e9partement d'Informatique - Facult\u00e9 d'Electronique et d'Informatique\r\nUniversit\u00e9 des Sciences et de la Technologie Houari Boumediene, BP 32 EL Alia 16111 Bab Ezzouar Alger. - Algeria)"],"affiliations":[{"raw_affiliation_string":"Univ. of Sciences and Technology Houari Boumediene (Algeria)","institution_ids":["https://openalex.org/I157169809"]},{"raw_affiliation_string":"D\u00e9partement d'Informatique, Laboratoire RIIMA, USTHB (Laboratoire RIIMA - D\u00e9partement d'Informatique - Facult\u00e9 d'Electronique et d'Informatique\r\nUniversit\u00e9 des Sciences et de la Technologie Houari Boumediene, BP 32 EL Alia 16111 Bab Ezzouar Alger. - Algeria)","institution_ids":["https://openalex.org/I157169809"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083173024","display_name":"Yannick Benezeth","orcid":"https://orcid.org/0000-0002-6034-7431"},"institutions":[{"id":"https://openalex.org/I157169809","display_name":"University of Sciences and Technology Houari Boumediene","ror":"https://ror.org/02kb89c09","country_code":"DZ","type":"education","lineage":["https://openalex.org/I157169809"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Yannick BENEZETH","raw_affiliation_strings":["Univ. Burgundy (France)","University of Sciences and Technology Houari Boumediene, LRIA"],"affiliations":[{"raw_affiliation_string":"Univ. Burgundy (France)","institution_ids":[]},{"raw_affiliation_string":"University of Sciences and Technology Houari Boumediene, LRIA","institution_ids":["https://openalex.org/I157169809"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113249515","display_name":"Feryel Souami","orcid":null},"institutions":[{"id":"https://openalex.org/I157169809","display_name":"University of Sciences and Technology Houari Boumediene","ror":"https://ror.org/02kb89c09","country_code":"DZ","type":"education","lineage":["https://openalex.org/I157169809"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Feryel SOUAMI","raw_affiliation_strings":["Univ. of Sciences and Technology Houari Boumediene (Algeria)","CORES - Equipe CORES [ImViA - EA7535] (Dijon - France)"],"affiliations":[{"raw_affiliation_string":"Univ. of Sciences and Technology Houari Boumediene (Algeria)","institution_ids":["https://openalex.org/I157169809"]},{"raw_affiliation_string":"CORES - Equipe CORES [ImViA - EA7535] (Dijon - France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055175308"],"corresponding_institution_ids":["https://openalex.org/I157169809"],"apc_list":null,"apc_paid":null,"fwci":0.2944,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.54405239,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"74","last_page":"74"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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":0.9980999827384949,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9901000261306763,"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/codebook","display_name":"Codebook","score":0.8139804601669312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7957291007041931},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7076401114463806},{"id":"https://openalex.org/keywords/bag-of-words-model-in-computer-vision","display_name":"Bag-of-words model in computer vision","score":0.6572157740592957},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.597904622554779},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5864996910095215},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5669921040534973},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5176406502723694},{"id":"https://openalex.org/keywords/activity-recognition","display_name":"Activity recognition","score":0.514155387878418},{"id":"https://openalex.org/keywords/bag-of-words-model","display_name":"Bag-of-words model","score":0.4426235556602478},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.43337857723236084},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4203195571899414},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39459845423698425},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.36855706572532654},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20108342170715332},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.16474613547325134}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.8139804601669312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7957291007041931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7076401114463806},{"id":"https://openalex.org/C167611913","wikidata":"https://www.wikidata.org/wiki/Q6884747","display_name":"Bag-of-words model in computer vision","level":5,"score":0.6572157740592957},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.597904622554779},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5864996910095215},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5669921040534973},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5176406502723694},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.514155387878418},{"id":"https://openalex.org/C13672336","wikidata":"https://www.wikidata.org/wiki/Q3460803","display_name":"Bag-of-words model","level":2,"score":0.4426235556602478},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.43337857723236084},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4203195571899414},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39459845423698425},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.36855706572532654},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20108342170715332},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.16474613547325134},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1117/12.2559268","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2559268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Twelfth International Conference on Machine Vision (ICMV 2019)","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2158102958","https://openalex.org/W1615295117","https://openalex.org/W2035094092","https://openalex.org/W2045213079","https://openalex.org/W2938717424","https://openalex.org/W2277784908","https://openalex.org/W2179703327","https://openalex.org/W2587721114","https://openalex.org/W2032791227","https://openalex.org/W2518262377"],"abstract_inverted_index":{"Bag":[0],"of":[1,34,41,66,82,100,160,176,180,195],"Visual":[2],"Words":[3],"Model":[4],"(BoVW)":[5],"has":[6],"achieved":[7],"impressive":[8],"performance":[9],"on":[10,63,107,137,188],"human":[11,60],"activity":[12],"recognition.":[13],"However,":[14],"it":[15],"is":[16,37,86,154,170],"extremely":[17],"difficult":[18],"to":[19,96,156,163,198],"capture":[20],"high-level":[21,59],"semantic":[22],"meanings":[23],"behind":[24],"video":[25,134],"features":[26,110,116,123,162],"with":[27,205],"this":[28,48,108],"method":[29,197],"as":[30],"the":[31,42,78,83,89,98,104,132,151,174,177,189,193,200],"spatiotemporal":[32,67,142],"distribution":[33],"visual":[35,68,161,181],"words":[36,182],"ignored,":[38],"preventing":[39],"localization":[40],"interactions":[43,202],"within":[44],"a":[45,52,64,72,158,165,206],"video.":[46],"In":[47],"paper,":[49],"we":[50],"propose":[51],"supervised":[53],"learning":[54],"framework":[55],"that":[56,76],"automatically":[57],"recognizes":[58],"interaction":[61,169],"based":[62],"bag":[65],"features.":[69],"At":[70],"first,":[71],"representative":[73],"baseline":[74],"keyframe":[75],"captures":[77],"major":[79],"body":[80],"parts":[81],"interacting":[84,126,148],"persons":[85,93,102],"selected":[87],"and":[88,117,128],"bounding":[90],"boxes":[91],"containing":[92],"are":[94,111,144],"extracted":[95],"parse":[97],"poses":[99],"all":[101],"in":[103],"interaction.":[105,167],"Based":[106,136],"keyframe,":[109],"detected":[112],"by":[113,173],"combining":[114],"edge":[115],"Maximally":[118],"Stable":[119],"Extremal":[120],"Regions":[121],"(MSER)":[122],"for":[124,146],"each":[125,147],"person":[127],"backward-forward":[129],"tracked":[130],"over":[131],"entire":[133],"sequence.":[135],"feature":[138],"tracks,":[139],"3D":[140],"XYT":[141],"volumes":[143],"generated":[145],"target.":[149],"Then,":[150],"K-means":[152],"algorithm":[153],"used":[155],"build":[157],"codebook":[159],"represent":[164],"given":[166],"The":[168],"then":[171],"represented":[172],"sum":[175],"frequency":[178],"occurrence":[179],"between":[183],"persons.":[184],"Extensive":[185],"experimental":[186],"evaluations":[187],"UT-interaction":[190],"dataset":[191],"demonstrate":[192],"strength":[194],"our":[196],"recognize":[199],"ongoing":[201],"from":[203],"videos":[204],"simple":[207],"implementation.":[208]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2025-10-10T00:00:00"}