{"id":"https://openalex.org/W4416136759","doi":"https://doi.org/10.1109/ipta66025.2025.11222029","title":"A Modular System for Human Action Detection Combining YOLO and Transformer-Based Video Understanding","display_name":"A Modular System for Human Action Detection Combining YOLO and Transformer-Based Video Understanding","publication_year":2025,"publication_date":"2025-10-13","ids":{"openalex":"https://openalex.org/W4416136759","doi":"https://doi.org/10.1109/ipta66025.2025.11222029"},"language":null,"primary_location":{"id":"doi:10.1109/ipta66025.2025.11222029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipta66025.2025.11222029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Fourteenth International Conference on Image Processing, Theory, Tools & Applications (IPTA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5035844840","display_name":"Awatef Edhib","orcid":null},"institutions":[{"id":"https://openalex.org/I100532134","display_name":"Lyon 1 Universit\u00e9","ror":"https://ror.org/029brtt94","country_code":"FR","type":"education","lineage":["https://openalex.org/I100532134","https://openalex.org/I203339264"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Awatef Edhib","raw_affiliation_strings":["Claude Bernard Lyon 1 University,Lyon,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Claude Bernard Lyon 1 University,Lyon,France","institution_ids":["https://openalex.org/I100532134"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120493350","display_name":"Achraf Chabbouh","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Achraf Chabbouh","raw_affiliation_strings":["Anavid Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anavid Ltd","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090338398","display_name":"Ahmed Chaari","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ahmed Chaari","raw_affiliation_strings":["Anavid Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anavid Ltd","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082453205","display_name":"Rostom Kachouri","orcid":"https://orcid.org/0000-0002-9451-4269"},"institutions":[{"id":"https://openalex.org/I4210152518","display_name":"Laboratoire d'Informatique Gaspard-Monge","ror":"https://ror.org/04t50yk91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I142631665","https://openalex.org/I4210145102","https://openalex.org/I4210152518","https://openalex.org/I4210154111","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I4210154111","display_name":"Universit\u00e9 Gustave Eiffel","ror":"https://ror.org/03x42jk29","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210154111"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Rostom Kachouri","raw_affiliation_strings":["Gustave Eiffel University,LIGM Laboratory, A3SI Team, ESIEE Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gustave Eiffel University,LIGM Laboratory, A3SI Team, ESIEE Paris,France","institution_ids":["https://openalex.org/I4210152518","https://openalex.org/I4210154111"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37861641,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.8726000189781189,"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":0.8726000189781189,"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":0.04619999974966049,"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":0.03779999911785126,"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/robustness","display_name":"Robustness (evolution)","score":0.6794999837875366},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5922999978065491},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5695000290870667},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5198000073432922},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.45399999618530273},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.451200008392334},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.40619999170303345},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.3840999901294708},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.37220001220703125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7508999705314636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7063999772071838},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6794999837875366},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5922999978065491},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5695000290870667},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5198000073432922},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5134000182151794},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.45399999618530273},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.451200008392334},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.40619999170303345},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3666999936103821},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C2778949103","wikidata":"https://www.wikidata.org/wiki/Q600717","display_name":"Staring","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32330000400543213},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.31290000677108765},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2833000123500824},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C2780624872","wikidata":"https://www.wikidata.org/wiki/Q852453","display_name":"Motion detection","level":3,"score":0.2678999900817871},{"id":"https://openalex.org/C117035363","wikidata":"https://www.wikidata.org/wiki/Q3769299","display_name":"Human behavior","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2628999948501587}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipta66025.2025.11222029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipta66025.2025.11222029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Fourteenth International Conference on Image Processing, Theory, Tools & Applications (IPTA)","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":5,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2507009361","https://openalex.org/W2618799552","https://openalex.org/W2963524571","https://openalex.org/W4297697565"],"related_works":[],"abstract_inverted_index":{"The":[0],"accurate":[1],"detection":[2,67,79],"of":[3,58,68,85,101,145,150,168],"suspicious":[4,69],"human":[5],"actions,":[6],"such":[7],"as":[8],"shoplifting,":[9],"in":[10,71,115],"surveillance":[11,174],"videos":[12],"is":[13],"critical":[14],"for":[15,171],"ensuring":[16],"public":[17],"safety":[18],"and":[19,24,40,120,139,147,157,165,178],"enabling":[20],"long-term":[21],"crime":[22],"prevention":[23],"crowd":[25],"trust.":[26],"However,":[27],"this":[28,45],"task":[29],"remains":[30],"challenging":[31,133],"due":[32],"to":[33,64,81,95],"complex":[34],"scene":[35,118],"dynamics,":[36],"varying":[37],"camera":[38,140],"viewpoints,":[39],"imbalanced":[41],"data":[42,121],"distributions.":[43],"In":[44],"paper,":[46],"we":[47,107],"propose":[48],"a":[49,92,104,143],"new":[50],"action":[51,180],"recognition":[52],"framework":[53,125],"integrating":[54],"fine-grained":[55],"spatial":[56],"localization":[57],"individuals":[59],"with":[60],"transformer-based":[61],"temporal":[62,93],"modeling":[63],"enhance":[65],"person-level":[66],"behaviors":[70],"retail":[72,173],"environments.":[73],"Our":[74],"approach":[75,170],"leverages":[76],"state-of-the-art":[77],"object":[78],"techniques":[80],"extract":[82],"per-person":[83],"regions":[84],"interest,":[86],"which":[87],"are":[88],"then":[89],"processed":[90],"by":[91,155],"encoder":[94],"effectively":[96],"capture":[97],"motion":[98],"patterns":[99],"indicative":[100],"shoplifting.":[102],"Through":[103],"gap":[105],"analysis,":[106],"identify":[108],"that":[109,123],"existing":[110],"methods":[111],"often":[112],"fall":[113],"short":[114],"handling":[116],"diverse":[117],"conditions":[119],"imbalance\u2014issues":[122],"our":[124,130,169],"explicitly":[126],"addresses.":[127],"We":[128],"evaluate":[129],"method":[131],"on":[132],"datasets":[134],"featuring":[135],"varied":[136],"store":[137],"layouts":[138],"angles,":[141],"achieving":[142],"sensitivity":[144],"91.34%":[146],"an":[148],"accuracy":[149],"82.45%,":[151],"surpassing":[152],"the":[153,163],"baseline":[154],"33%":[156],"21%,":[158],"respectively.":[159],"These":[160],"results":[161],"highlight":[162],"robustness":[164],"practical":[166],"relevance":[167],"real-world":[172],"applications":[175],"requiring":[176],"reliable":[177],"interpretable":[179],"recognition.":[181]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-11-10T00:00:00"}