{"id":"https://openalex.org/W4389474561","doi":"https://doi.org/10.1109/mmsp59012.2023.10337696","title":"ConViViT - A Deep Neural Network Combining Convolutions and Factorized Self-Attention for Human Activity Recognition","display_name":"ConViViT - A Deep Neural Network Combining Convolutions and Factorized Self-Attention for Human Activity Recognition","publication_year":2023,"publication_date":"2023-09-27","ids":{"openalex":"https://openalex.org/W4389474561","doi":"https://doi.org/10.1109/mmsp59012.2023.10337696"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp59012.2023.10337696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp59012.2023.10337696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 25th International Workshop on Multimedia Signal Processing (MMSP)","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/A5093446602","display_name":"Dokkar Rachid Reda","orcid":null},"institutions":[{"id":"https://openalex.org/I117841876","display_name":"Universit\u00e9 Paris-Panth\u00e9on-Assas","ror":"https://ror.org/04qb2qm38","country_code":"FR","type":"education","lineage":["https://openalex.org/I117841876"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Dokkar Rachid Reda","raw_affiliation_strings":["Paris Panthéon-Assas University,Efrei Research Lab,Paris,France"],"affiliations":[{"raw_affiliation_string":"Paris Panthéon-Assas University,Efrei Research Lab,Paris,France","institution_ids":["https://openalex.org/I117841876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015939203","display_name":"Faten Chaieb","orcid":"https://orcid.org/0000-0002-2968-2426"},"institutions":[{"id":"https://openalex.org/I117841876","display_name":"Universit\u00e9 Paris-Panth\u00e9on-Assas","ror":"https://ror.org/04qb2qm38","country_code":"FR","type":"education","lineage":["https://openalex.org/I117841876"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Faten Chaieb","raw_affiliation_strings":["Paris Panthéon-Assas University,Efrei Research Lab,Paris,France"],"affiliations":[{"raw_affiliation_string":"Paris Panthéon-Assas University,Efrei Research Lab,Paris,France","institution_ids":["https://openalex.org/I117841876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037290359","display_name":"Hassen Drira","orcid":"https://orcid.org/0000-0003-1052-4353"},"institutions":[{"id":"https://openalex.org/I68947357","display_name":"Universit\u00e9 de Strasbourg","ror":"https://ror.org/00pg6eq24","country_code":"FR","type":"education","lineage":["https://openalex.org/I68947357"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Hassen Drira","raw_affiliation_strings":["Université de Strasbourg,ICube UMR 7357, CNRS,Strasbourg,France"],"affiliations":[{"raw_affiliation_string":"Université de Strasbourg,ICube UMR 7357, CNRS,Strasbourg,France","institution_ids":["https://openalex.org/I68947357","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063875333","display_name":"Arezki Aberkane","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arezki Aberkane","raw_affiliation_strings":["Caplogy SAS,Vélizy-Villacoubay,France"],"affiliations":[{"raw_affiliation_string":"Caplogy SAS,Vélizy-Villacoubay,France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5093446602"],"corresponding_institution_ids":["https://openalex.org/I117841876"],"apc_list":null,"apc_paid":null,"fwci":0.4745,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66128211,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9991000294685364,"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":0.9948999881744385,"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":0.824579656124115},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7275179624557495},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.6846092343330383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6165334582328796},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5646375417709351},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5136927962303162},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5017261505126953},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4633773863315582},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.433065265417099},{"id":"https://openalex.org/keywords/activity-recognition","display_name":"Activity recognition","score":0.413574755191803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.824579656124115},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7275179624557495},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6846092343330383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6165334582328796},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5646375417709351},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5136927962303162},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5017261505126953},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4633773863315582},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.433065265417099},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.413574755191803},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mmsp59012.2023.10337696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp59012.2023.10337696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 25th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04338804v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04338804","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2023 IEEE 25th International Workshop on Multimedia Signal Processing (MMSP), Sep 2023, Poitiers, France. pp.1-6, ⟨10.1109/MMSP59012.2023.10337696⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W2126579184","https://openalex.org/W2948048211","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2963820951","https://openalex.org/W2984287396","https://openalex.org/W2990503944","https://openalex.org/W3000453931","https://openalex.org/W3034600407","https://openalex.org/W3035619757","https://openalex.org/W3087825408","https://openalex.org/W3108241103","https://openalex.org/W3126721948","https://openalex.org/W3129478823","https://openalex.org/W3138516171","https://openalex.org/W3175528717","https://openalex.org/W3177141386","https://openalex.org/W3195645930","https://openalex.org/W3205509891","https://openalex.org/W3210279979","https://openalex.org/W3213269132","https://openalex.org/W4214612132","https://openalex.org/W4221166842","https://openalex.org/W4225278894","https://openalex.org/W4287639320","https://openalex.org/W6600983433","https://openalex.org/W6746563140","https://openalex.org/W6756911974","https://openalex.org/W6763795729","https://openalex.org/W6773432124","https://openalex.org/W6783346497","https://openalex.org/W6784291217","https://openalex.org/W6787292255","https://openalex.org/W6787859097","https://openalex.org/W6790307280","https://openalex.org/W6800214383","https://openalex.org/W6800563632","https://openalex.org/W6802441125","https://openalex.org/W6810661123"],"related_works":["https://openalex.org/W3195649134","https://openalex.org/W4293226380","https://openalex.org/W2281498195","https://openalex.org/W2017526120","https://openalex.org/W2610664080","https://openalex.org/W2188304107","https://openalex.org/W2761510556","https://openalex.org/W4321487865","https://openalex.org/W2892259437","https://openalex.org/W4313906399"],"abstract_inverted_index":{"The":[0],"Transformer":[1],"architecture":[2,121,181],"has":[3,90,182],"gained":[4],"significant":[5],"popularity":[6],"in":[7,95,118],"computer":[8],"vision":[9],"tasks":[10],"due":[11],"to":[12,15,56,136,169],"its":[13],"capacity":[14],"generalize":[16],"and":[17,45,72,79,116,191,196],"capture":[18],"long-range":[19],"dependencies.":[20],"This":[21],"characteristic":[22],"makes":[23],"it":[24],"well-suited":[25],"for":[26,42,122,177],"generating":[27,142],"spatiotemporal":[28,171],"tokens":[29,59],"from":[30,154],"videos.":[31,128],"On":[32],"the":[33,39,62,83,96,111,138,149,152,155,158,161],"other":[34],"hand,":[35],"convolutions":[36],"serve":[37],"as":[38,47],"fundamental":[40],"backbone":[41],"processing":[43],"images":[44],"videos,":[46],"they":[48],"efficiently":[49],"aggregate":[50],"information":[51],"within":[52],"small":[53],"local":[54],"neighborhoods":[55],"create":[57],"spatial":[58,63],"that":[60,109,146],"describe":[61],"dimension":[64],"of":[65,86,98,113,160],"a":[66,106,133,143,167],"video.":[67],"While":[68],"both":[69,114],"CNN-based":[70],"architectures":[71,75],"pure":[73],"transformer":[74,168],"are":[76,174],"extensively":[77],"studied":[78],"utilized":[80],"by":[81,141],"researchers,":[82],"effective":[84],"combination":[85],"these":[87],"two":[88],"backbones":[89],"not":[91],"received":[92],"comparable":[93],"attention":[94],"field":[97],"activity":[99,124,153],"recognition.":[100],"In":[101],"this":[102],"research,":[103],"we":[104,130],"propose":[105],"novel":[107],"approach":[108],"leverages":[110],"strengths":[112],"CNNs":[115],"Transformers":[117],"an":[119],"hybrid":[120],"performing":[123,151],"recognition":[125],"using":[126],"RGB":[127],"Specifically,":[129],"suggest":[131],"employing":[132],"CNN":[134,162],"network":[135],"enhance":[137],"video":[139,145],"representation":[140],"128-channel":[144],"effectively":[147],"separates":[148],"human":[150],"background.":[156],"Subsequently,":[157],"output":[159],"module":[163],"is":[164],"fed":[165],"into":[166],"extract":[170],"tokens,":[172],"which":[173],"then":[175],"used":[176],"classification":[178],"purposes.":[179],"Our":[180],"achieved":[183],"new":[184],"SOTA":[185],"results":[186],"with":[187],"90.05":[188],"%,":[189],"99.6%,":[190],"95.09%":[192],"on":[193],"HMDB51.":[194],"UCF101.":[195],"ETRI-Activity3D":[197],"respectively.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2023-12-09T00:00:00"}